SlideShare a Scribd company logo
由點、線至面:從影像分析角度
探討漫畫的組成與風格
朱威達
中正大學資訊工程學系
wtchu@ccu.edu.tw
1
Fair Use Declaration
• This statement is submitted for elaborating the legitimate status for illustrating all the “Screen Printings” and
“Comics” in the “由點、線至面:從影像分析角度探討漫畫的組成與風格” are cited under the doctrine of “Fair
Use” for research purpose if copyright protection applies on them.
• The legal doctrine establishes globally that originality is needed to be seen for a work pursuing copyright protection,
namely, the originality is the very essence of creation in intellectual domain. On account of that, an automatically
recorded screen motion of the interactive computer games can be deemed as no copyright protection on it,
therefore it can be lawfully applied in the “由點、線至面:從影像分析角度探討漫畫的組成與風格” as part of
the research materials without the written permission from the copyright owner of the computer games. However,
some people might treat them as copyright protected materials still for the drawings or similar creations in the
background of the animations or comics, if that applies, according to the international intellectual property
agreements and copyright law in respective jurisdictions, such as Agreement on Trade-Related Aspects of
Intellectual Property Rights (TRIPS) article 13, Berne Convention for the Protection of Literary and Artistic Works
article 9(2), EU Copyright Directive article 5(5), Copyright Law of the United States of America section 107 and
Taiwan Copyright Act article 65, the Fair Use and Fair Dealing of a copyrighted work based on teaching, scholarship,
or research shall applied under the circumstances to sustain the citation for all the “Screen Printings“ and “Comics”
in the “由點、線至面:從影像分析角度探討漫畫的組成與風格” as legitimate action abided by at law, which do
not conflict with a normal exploitation of the works and do not unreasonably prejudice the legitimate interests of
the right holders.
2
Introduction
• Comics-based presentation for
movie, animation, and photos,
emerges recently.
• Comics are believed to be an ideal
medium for visual storytelling
because of rich expressivity, high
interactivity, and high portability.
3
Sample generated comic pages from the animation “Neon Genesis
Evangelion” (top) and from the animation “Summer Wars” (bottom).
Introduction
Three key constituents of manga [1].
1. Drawing/絵絵絵絵
2. Language/言葉言葉言葉言葉
3. Panel/コマコマコマコマ
4[1] 夏目 房之介 (1997). マンガはなぜ面白いのか―その表現と文法. NHKライブラリー.
點
線
面
Drawing
Panel
Outline
• Part 1: Manga Style Analysis
• Part 2: Comics-based Storytelling
5
Motivation
• As the internet and mobile devices become popular, digital mangas
are widely accessible.
• Different mangas may have different styles. We focus on which
features can be used to distinguish different manga styles.
6
From bounding box of each panel, we
extract features to describe characteristics
of layout.
1) : average panel height
(derived from bounding boxes)
2) : average panel width
3) : standard deviation of
4) : standard deviation of
7
Panel Feature Extraction
5) : the ratio of total panel area to the
whole page
6) : average panel area
7) : standard deviation of
8) : average slope of vertical panel
boundaries
9) : average slope of horizontal panel
boundaries
10) : standard deviation of
11) : standard deviation of
8
Panel Feature Extraction
9
Panel Feature Extraction
Top row: sample manga pages from three different artists.
Bottom row: panel feature distributions corresponding to these pages.
Screentone Detection
11
• Screentone is a technique for applying textures
and shades to drawings, used as an alternative to hatching.
• Different authors have different habits to use screentone.
Screentone Detection
11
1. Image binarization.
2. Dilation.
3. Delete small areas.
4. Get screentone areas.
5. Extract patches from screentone
areas.
Screentone Feature Extraction
12
• Two screentone features are proposed:
– The ratio of screentone areas to the whole panel area ( ).
– Bag of screentone ( ).
• Gabor wavelet texture
• Use affinity propagation to cluster features, and use the bag of
word model to describe screentone.
B.J. Frey and D. Dueck. Clustering by passing messages between data points. Science, 2007.
Screentone Feature Extraction
13
Top row: sample manga pages from three different artists.
Bottom row: the BoP distributions corresponding to these artists.
Character Detection
14
• Apply the eye detection model in a sliding window manner to detect eyes.
• Expand the areas from eye regions. The big regions extended by all detected eye
regions are then covered by a minimum bounding box, which is finally the
determined character’s head region.
Line Feature Extraction
15
• Canny edge detection
• Edge linking
P. Kovesi, School of Computer Science & Software Engineering, The
University of Western Australia, http://www.csse.uwa.edu.au, 2001.
(1) Face image (2) Canny edge
image
(3) Edge linking (4) Straight line
segmentation.
Line Feature Extraction
16
• Included angle between lines ( ): For two spatially adjacent segment
lines, we calculate the included angle between them. The feature can be
represented as a 12-dimensional histogram.
Shonen
Shojo
Line Feature Extraction
• Line orientation ( ): Orientation of a line segment is defined as
the included angle between it and the horizontal axis. The feature
can be represented as a 12-dimensional orientation histogram.
17
Mitsuru Adachi
Terajima Yuji
Line Feature Extraction
18
• Density of line segments ( ): We calculate the number of lines in its
neighborhood, and the information over all line segments are gathered to
form the feature. It can be represented by 20-dimensional histogram.
Mitsuru Adachi
Terajima Yuji
Line Feature Extraction
19
• Orientation of nearby lines ( ): Orientations of a line segment’s
nearby lines are calculated, in the representation of a 12-dimensional
orientation histogram
Mitsuru Adachi
Terajima Yuji
Line Feature Extraction
• Number of nearby lines with similar orientation ( ): To a line
segment L, we calculate the number of its nearby lines that have
similar orientation to L. Such information over all line segments is
gathered to form a 20-dimensional histogram.
20
Shonen
Shojo
Line Feature Extraction
21
• Line strength varied ( ): We use twenty different threshold
settings for Canny edge detection. The ratio of detection results
to standard result is the feature. It is a 20-
dimensional vector .
Shonen
Shojo
Feature Analysis
23
• Comparison between mangas of different types of magazines.
Shone manga: 3 different mangas, totally 300 pages.
Shojo manga: 3 different mangas, totally 300 pages.
(4) “ I love flowers and Mr.”,
Kumaoka Fuyuyu.
(5) “ The first love honey”,
Minase Ai.
(6) “ From me to you”,
Shiina Karuho.
(1) “Nisekoi”, Komi Naoshi. (2) “ Yamada-kun and the seven
witches”, Miki Yoshikawa.
(3) “ Agatsuma's my daughter”,
Nishikida Keikokorozashi.
Feature Analysis
23
– Comparison between mangas with the same topic but
drawn by different artists.
– Use statistical comparison to analyze the proposed
features.
Baseball manga: 3 different mangas, totally 300 pages.
(1) “Ace of Diamond”, Terajima
Yuji.
(2) “Mix”, Mitsuru Adachi. (3) “Big Windup”,
Mizushima Tsutomu.
Feature Analysis
24
– Comparison between mangas of different types of
magazines.
P-value 0.039 0.414 0.151 0.429 0.017 0.003 0.044 0.000
Shonen Shojo
Feature Analysis
25
• Distance map (Shonen mangas v.s Shojo mangas):
( : 0.017)
( : 0.003)
( : 0.414) ( : 0.429)
shonen
shonen shojo
shojo
Feature Analysis
26
– Comparison between mangas with the same topic but drawn by
different artists.
– P-value:
TY v.s MA 0.037 0.183 0.000 0.277 0.000 0.000 0.6 0.000
TY v.s MT 0.105 0.006 0.075 0.007 0.199 0.074 0.47 0.000
MA v.s MT 0.325 0.091 0.161 0.061 0.011 0.000 0.14 0.000
Terajima Yuji (TY) Mitsuru Adachi (MA) Mizuhima Tsutomu (MT)
Feature Analysis
27
• Spider chart (based on skewness of features):
Feature Analysis
34
• Comparison between mangas of different types of magzines.
– SVM test: 5-fold cross-validation.
– Comparison between mangas with the same topic but drawn by
different artists.
– SVM test: 5-fold cross-validation
accuracy 71.6 61.5 60.5 56.8 70.3 74.5 82 75 79.3 80
TY v.s MA 74.2 64.2 70 62.1 77.8 90.7 90 63.3 71.6 72
TY v.s MT 65 72.8 62.8 72.8 50 69.2 76.1 56.6 88 88
MA v.s MT 71.4 67.1 64.2 68.5 74.2 86.4 86.1 66.6 82 81
Latent Style Model
• Developing a style model based on Latent Dirichlet Allocation (LDA)
to discover style elements.
• Documents can be represented as mixtures of latent topics, where
each topic is formed by a distribution over words.
29
……
1 2 3
Document Topic Word
~
~
, ,
Blei, D. M., Ng, A. Y., & Jordan, M. I. (2003). Latent dirichlet allocation. Journal of Machine Learning Research, 3,
993-1022.
Latent Style Model
30
Attribute of Latent Dirichlet
Allocation
Text document Latent topics Word
Attribute of Latent Style
Model
Manga pages of the
same artist
Latent style elements Visual word
(manga page)
Given a set of documents , … , ! with the observed visual
words, we can efficiently learn the model by the Gibbs sampling
algorithm.
Style probabilities of a document can be estimated, which enable
us to represent a document as a distribution of style elements.
31
Style Element Distributions
Top: sample manga pages from three different documents.
Bottom: style element distributions corresponding to these documents.
Artists in Dataset 1
32
(F)“天地を喰らう”,本宮 ひろ志.
(G)“北斗の拳”,原 哲夫.
(H)“魁!!男塾”,宮下 あきら.
(C) “うしおととら”,藤田 和日郎.
(D)“金色のガッシュ!!”,雷句 誠.
(E)“呪法解禁!!”,麻生 羽呂.
(A)“Fairy Tail”,真島 ヒロ.
(B) “ヤンキー君とメガネちゃん”,吉河 美希.
(A) (B) (D)(C) (E)
(F) (G) (H)
100 manga pages from eight different
artists, consisting of totally 800 manga
pages.
Art Movement in Dataset 1
33
34
(B) “ヤンキー君とメガネちゃん”
吉河 美希.
(E) “呪法解禁!!”
麻生 羽呂.
(G)“北斗の拳”
原 哲夫.
Artist Style Element Distributions
Top: sample manga pages from three different artists.
Bottom: style element distributions corresponding to these artists.
Style-Based Art Movement Retrieval
35
Given a query, we would like to retrieve manga documents
produced by artists of the same movement.
0.65
0.7
0.75
0.8
0.85
0.9
10 styles 20 styles 30 styles 40 styles
MAP@10
hist. intersection(line features) chi-square(line features)
hist. intersection(all features) chi-square(all features)
distance
measure
10
styles
20
styles
30 styles 40 styles
line
features
histogram
intersection
0.7093 0.7152 0.7329 0.7158
line
features
chi square 0.7024 0.719 0.7443 0.7383
all features
histogram
intersection
0.8413 0.8472 0.8483 0.8125
all features chi square 0.8358 0.8518 0.8544 0.8196
MAP@10
Style-Based Artist Retrieval
36
Given an artist’s manga document, we would like to retrieve
other documents produced by the same artist.
0.55
0.6
0.65
0.7
0.75
0.8
0.85
10 styles 20 styles 30 styles 40 styles
MAP@10
hist. intersection(line features) chi-square(line features)
hist. intersection(all features) chi-square(all features)
distance
measure
10
styles
20
styles
30 styles 40 styles
line
features
histogram
intersection
0.6401 0.6404 0.6460 0.6323
line
features
chi square 0.6385 0.6457 0.6541 0.6537
all features
histogram
intersection
0.7627 0.7663 0.7854 0.7654
all features chi square 0.7470 0.7553 0.7939 0.7824
MAP@10
Artwork Period Retrieval
We take the manga JoJo's Bizarre Adventure for analysis, which is
created by Hirohiko Araki from 1987 to now. Totally 300 pages.
37
ジョジョの奇妙な冒険
Part 3 (1989-1992)
ジョジョの奇妙な冒険
Part 8 (2011-ongoing)
ジョジョの奇妙な冒険
Part 1 (1987)
Sample results of the query and top returned documents.
38
Artwork Period Retrieval
39
Given an artist’s manga document, we would like to retrieve
other documents produced by the same period.
0.5
0.55
0.6
0.65
0.7
0.75
10 styles 20 styles 30 styles 40 styles
MAP@10
hist. intersection(line features) chi-square(line features)
hist. intersection(all features) chi-square(all features)
distance
measure
10
styles
20
styles
30 styles 40 styles
line
features
histogram
intersection
0.5703 0.6247 0.6377 0.6428
line
features
chi square 0.5779 0.6446 0.6581 0.6622
all features
histogram
intersection
0.6321 0.6521 0.6698 0.6751
all features chi square 0.6376 0.6641 0.6781 0.6899
MAP@10
Artwork Period Retrieval
Summary
• Manga style analysis
– Manga-specific features
– Based on LDA, implicit style elements are discovered in a
probabilistic framework.
– Analysis can be achieved at the style level rather than the
feature level.
• Applications
– Style-based browsing
– Influence discovery
– Relationship between style and other properties
40
Part 2: Comics-Based Storytelling
朱威達
中正大學資訊工程學系
wtchu@ccu.edu.tw
41
Comics-Based Storytelling
• Goal: Develop a systematic framework to enable comics-based
storytelling of temporal image sequences
– Comic design theory
– Formulate core components as optimization problems and
systematically solve them
– Interactivity
42
Challenges
• Q1. How to segment the given temporal image sequence, so that
images in the same subsequence present similar
semantics/events/scenes and are appropriately to be put into the
same comic page?
43
Challenges
• Q2. What is the best layout to arrange panels in the same page?
44
?? ?
Challenges
• Q3. How to place speech balloons, so that important content in
images are not occluded by balloons, and balloons’ positions direct
viewer’s gaze to build a pleasing reading trajectory?
45
Optimized Page Allocation
• Allocate appropriate number of comic pages that may include
various numbers of cells.
– Visual coherence: Consecutive or similar visual content tends to be put into
the same comic page.
– Browsing pace: Keyframes conveying high motion are tended to be put into
the same pages containing more panels to build tense browsing experience.
• A labeling problem, with the temporal continuity constraint
– Solution: Genetic algorithm (GA)
46
1 1 1 2 2 2 2 3 3 4 4 4
Q1. How to segment the given temporal image sequence?
Optimized Page Allocation
47
1 1 1 2 2 2 2 3 3 4 4 4
Objective Function (Fitness)
Page 1
Page 2
Page 3
Page 1
Page 2
Page 1
Page 2
At the 5th iteration
At the 20th iteration
At the 90th iteration
0.7
0.75
0.8
0.85
0.9
0.95
1 11 21 31 41 51 61 71 81 91 101
Best
Average
Worst
5th iteration
20th iteration
90th iteration
48
Iteration
fitness
Optimized Layout Selection
• Desired properties
– More important images should be allocated larger panels
– Keyframes extracted from the same shot or photos
consecutively taken in the same place are better to be put in the
same row of panels
– Keyframes with more subtitle words or photos with more
annotation are to be allocated larger panels.
• Idea
– Determine the images-layout pair that has the most similar
“importance” distributions.
49
Q2. What is the best layout to arrange panels in the same page?
Image Importance
• From each keyframe, the region of interest (ROI) is extracted based
on color contrast [Cheng’11].
• Assume that the keyframes are determined to put
at the same page. The importance value of a keyframe is defined as
ratio of the area
of ROI
ratio of the number of
subtitle words
the minimum color histogram distance
from this frame to other frames
50
M.-M. Cheng, G.-X. Zhang, N.J. Mitra, X. Huang, and S.-M. Hu. “Global contrast based salient region detection.” Proc. of IEEE Conference on Computer Vision
and Pattern Recognition, pp. 409-416, 2011.
Layout Design
51
...
...
...
.........
1 panel layout 2 panels layout 3 panels layout 4 panels layout
5 panel layout 6 panels layout 7 panels layout 8 panels layout
Layout Importance
• Layout importance
• To measure how appropriately a layout matches with the given
image sequence
– Inner product:
52
1/3
1/3
1/3
0.5
0.25 0.25
0.25 0.25
0.5 . . . . . . . .
: the ratio of the area of the jth panel to the area
of the whole page.
Layout Importance
• Binary vectors to show how panels are arranged into rows
– How different panel arrangements fit with shot:
• Importance distribution in terms of numbers of spoken words
– Inner product:
53
1st row
2nd row
3rd row
1st row
2nd row
r1=(01100) r2=(00110) r3=(01000)
1/3
1/3
1/3
0.5
0.25 0.25
0.25 0.25
0.5 . . . . . . . .
Layout Selection
54
r1=(011) r2=(010) r1=(001)
Shot # 1 2 2
Images
q 0 1 0
The best layout is selected by:
Crop
Paste+Resize
Find
ROI
Find
center
Extend
Composition
55
Layout Selection Comparison
56
Example 2: Layout selected by the
proposed method (c) and two
different equally-allocated layouts
(d)(e).
Example 1: Layout selected by the
proposed method (a) and by equal
allocation (b).
(a) (b)
(c) (d) (e)
Balloon Placement
• Optimal positions are determined by jointly considering the
following factors:
– Balloons should not overlap with the regions of interest (ROIs) in images.
– Balloons should be placed as close as the ROI in images.
– When there are multiple balloons in a panel, the sentences spoken earlier
should be placed closer to the left-top corner of the panel. This is to maintain
correct reading order.
– Balloons should not overlap with each other.
– Reading trajectory should be built so that reading order is not only correct
but also vivid.
57
Q3. How to place speech balloons?
Optimized Speech Balloon Placement
• Finally, the five factors are linearly
combined:
• This problem can be intuitively
mapped to the one efficiently solved
by the particle swarm optimization
algorithm (PSO).
58
local region
global region
59
Left: demonstration of PSO in
200 iterations
Right: ROI of comic page
Comparison of balloon placement considering different factors. (a)(c) The placement results if all factors are jointly
considered. (b) The placement result if overlapping between balloons is not taken into account. (d) The placement result
if overlapping between balloons and ROIs is not taken into account.
Optimized Speech Balloon Placement
Demo
60
Summary
61
• We have presented a system that automatically
transforms temporal image sequences into comics-based
storytelling.
– Optimized page allocation
– Optimized layout selection
– Optimized speech balloon placement
• Future work
– ROI analysis techniques specially designed for animation
– Investigation of semantics on automatic comics generation
Questions?
Wei-Ta Chu (朱威達)
National Chung Cheng University
wtchu@ccu.edu.tw
62

More Related Content

Viewers also liked

等速圓周運動 角位移角速度數學方程
等速圓周運動 角位移角速度數學方程等速圓周運動 角位移角速度數學方程
等速圓周運動 角位移角速度數學方程
阿Samn的物理課本
 
從技術角度看 RWD - Technical Approaches to RWD
從技術角度看 RWD - Technical Approaches to RWD從技術角度看 RWD - Technical Approaches to RWD
從技術角度看 RWD - Technical Approaches to RWD
Chris Wu
 
QM-065-從管理角度探討
QM-065-從管理角度探討QM-065-從管理角度探討
QM-065-從管理角度探討handbook
 
怎麼看電影Day2 筆記整理 230116
怎麼看電影Day2  筆記整理 230116怎麼看電影Day2  筆記整理 230116
怎麼看電影Day2 筆記整理 230116
gaowenwen
 
igdshare 110220: 以傳統程式開發者角度切入 Unity3D
igdshare 110220: 以傳統程式開發者角度切入 Unity3Digdshare 110220: 以傳統程式開發者角度切入 Unity3D
igdshare 110220: 以傳統程式開發者角度切入 Unity3D
igdshare
 
TechShanghai2016 - 从全局角度实现IC、封装和PCB的协同优化
TechShanghai2016 - 从全局角度实现IC、封装和PCB的协同优化TechShanghai2016 - 从全局角度实现IC、封装和PCB的协同优化
TechShanghai2016 - 从全局角度实现IC、封装和PCB的协同优化
Hardway Hou
 
2016 05 17_如何自企業經營角度,以最小成本、最大戰力,作出國防兵力的調整
2016 05 17_如何自企業經營角度,以最小成本、最大戰力,作出國防兵力的調整2016 05 17_如何自企業經營角度,以最小成本、最大戰力,作出國防兵力的調整
2016 05 17_如何自企業經營角度,以最小成本、最大戰力,作出國防兵力的調整
luckypeopleoftaiwan
 
我的BDD實踐
我的BDD實踐我的BDD實踐
我的BDD實踐
Huang Bruce
 
LWC18 編目館員看RDA的各種角度 報告人:國立臺灣大學圖書館書目服務組李明錦組長
LWC18 編目館員看RDA的各種角度 報告人:國立臺灣大學圖書館書目服務組李明錦組長LWC18 編目館員看RDA的各種角度 報告人:國立臺灣大學圖書館書目服務組李明錦組長
LWC18 編目館員看RDA的各種角度 報告人:國立臺灣大學圖書館書目服務組李明錦組長
International Federation for information integration
 
2004ASAP從社會福利角度看菸害防制
2004ASAP從社會福利角度看菸害防制 2004ASAP從社會福利角度看菸害防制
2004ASAP從社會福利角度看菸害防制
None
 
淺談測試Part2
淺談測試Part2淺談測試Part2
淺談測試Part2
Chris Chang
 
等速圓周運動 速率-加速度-數學方程
等速圓周運動 速率-加速度-數學方程等速圓周運動 速率-加速度-數學方程
等速圓周運動 速率-加速度-數學方程
阿Samn的物理課本
 
功夫微講堂第四卷
功夫微講堂第四卷功夫微講堂第四卷
功夫微講堂第四卷
美棻Nancy 魏Wei
 
邏輯性簡報建構法課程簡介 / 商業簡報網-韓明文講師
邏輯性簡報建構法課程簡介 / 商業簡報網-韓明文講師邏輯性簡報建構法課程簡介 / 商業簡報網-韓明文講師
邏輯性簡報建構法課程簡介 / 商業簡報網-韓明文講師
明文 韓
 
從open data角度談網站api應用
從open data角度談網站api應用從open data角度談網站api應用
從open data角度談網站api應用
Yu Shu Huang
 
計算社會學-江彥生
計算社會學-江彥生計算社會學-江彥生
計算社會學-江彥生
台灣資料科學年會
 
Learning for Big Data-林軒田
Learning for Big Data-林軒田Learning for Big Data-林軒田
Learning for Big Data-林軒田
台灣資料科學年會
 
海量視覺資料-孫民
海量視覺資料-孫民海量視覺資料-孫民
海量視覺資料-孫民
台灣資料科學年會
 
李宏毅/當語音處理遇上深度學習
李宏毅/當語音處理遇上深度學習李宏毅/當語音處理遇上深度學習
李宏毅/當語音處理遇上深度學習
台灣資料科學年會
 
Google TensorFlow Tutorial
Google TensorFlow TutorialGoogle TensorFlow Tutorial
Google TensorFlow Tutorial
台灣資料科學年會
 

Viewers also liked (20)

等速圓周運動 角位移角速度數學方程
等速圓周運動 角位移角速度數學方程等速圓周運動 角位移角速度數學方程
等速圓周運動 角位移角速度數學方程
 
從技術角度看 RWD - Technical Approaches to RWD
從技術角度看 RWD - Technical Approaches to RWD從技術角度看 RWD - Technical Approaches to RWD
從技術角度看 RWD - Technical Approaches to RWD
 
QM-065-從管理角度探討
QM-065-從管理角度探討QM-065-從管理角度探討
QM-065-從管理角度探討
 
怎麼看電影Day2 筆記整理 230116
怎麼看電影Day2  筆記整理 230116怎麼看電影Day2  筆記整理 230116
怎麼看電影Day2 筆記整理 230116
 
igdshare 110220: 以傳統程式開發者角度切入 Unity3D
igdshare 110220: 以傳統程式開發者角度切入 Unity3Digdshare 110220: 以傳統程式開發者角度切入 Unity3D
igdshare 110220: 以傳統程式開發者角度切入 Unity3D
 
TechShanghai2016 - 从全局角度实现IC、封装和PCB的协同优化
TechShanghai2016 - 从全局角度实现IC、封装和PCB的协同优化TechShanghai2016 - 从全局角度实现IC、封装和PCB的协同优化
TechShanghai2016 - 从全局角度实现IC、封装和PCB的协同优化
 
2016 05 17_如何自企業經營角度,以最小成本、最大戰力,作出國防兵力的調整
2016 05 17_如何自企業經營角度,以最小成本、最大戰力,作出國防兵力的調整2016 05 17_如何自企業經營角度,以最小成本、最大戰力,作出國防兵力的調整
2016 05 17_如何自企業經營角度,以最小成本、最大戰力,作出國防兵力的調整
 
我的BDD實踐
我的BDD實踐我的BDD實踐
我的BDD實踐
 
LWC18 編目館員看RDA的各種角度 報告人:國立臺灣大學圖書館書目服務組李明錦組長
LWC18 編目館員看RDA的各種角度 報告人:國立臺灣大學圖書館書目服務組李明錦組長LWC18 編目館員看RDA的各種角度 報告人:國立臺灣大學圖書館書目服務組李明錦組長
LWC18 編目館員看RDA的各種角度 報告人:國立臺灣大學圖書館書目服務組李明錦組長
 
2004ASAP從社會福利角度看菸害防制
2004ASAP從社會福利角度看菸害防制 2004ASAP從社會福利角度看菸害防制
2004ASAP從社會福利角度看菸害防制
 
淺談測試Part2
淺談測試Part2淺談測試Part2
淺談測試Part2
 
等速圓周運動 速率-加速度-數學方程
等速圓周運動 速率-加速度-數學方程等速圓周運動 速率-加速度-數學方程
等速圓周運動 速率-加速度-數學方程
 
功夫微講堂第四卷
功夫微講堂第四卷功夫微講堂第四卷
功夫微講堂第四卷
 
邏輯性簡報建構法課程簡介 / 商業簡報網-韓明文講師
邏輯性簡報建構法課程簡介 / 商業簡報網-韓明文講師邏輯性簡報建構法課程簡介 / 商業簡報網-韓明文講師
邏輯性簡報建構法課程簡介 / 商業簡報網-韓明文講師
 
從open data角度談網站api應用
從open data角度談網站api應用從open data角度談網站api應用
從open data角度談網站api應用
 
計算社會學-江彥生
計算社會學-江彥生計算社會學-江彥生
計算社會學-江彥生
 
Learning for Big Data-林軒田
Learning for Big Data-林軒田Learning for Big Data-林軒田
Learning for Big Data-林軒田
 
海量視覺資料-孫民
海量視覺資料-孫民海量視覺資料-孫民
海量視覺資料-孫民
 
李宏毅/當語音處理遇上深度學習
李宏毅/當語音處理遇上深度學習李宏毅/當語音處理遇上深度學習
李宏毅/當語音處理遇上深度學習
 
Google TensorFlow Tutorial
Google TensorFlow TutorialGoogle TensorFlow Tutorial
Google TensorFlow Tutorial
 

Similar to 由點、線至面:從影像分析角度探討漫畫的組成與風格-朱威達

427lects
427lects427lects
427lects
Praveen Kumar
 
Lecture1
Lecture1Lecture1
Lecture1
Mobeen Mustafa
 
Semi-automatic Picture Book Generation based on Story Model and Agent-based S...
Semi-automatic Picture Book Generation based on Story Model and Agent-based S...Semi-automatic Picture Book Generation based on Story Model and Agent-based S...
Semi-automatic Picture Book Generation based on Story Model and Agent-based S...
IJMREMJournal
 
Estimating the Crest Lines on Polygonal Mesh Models by an Automatic Threshold
Estimating the Crest Lines on Polygonal Mesh Models by an Automatic ThresholdEstimating the Crest Lines on Polygonal Mesh Models by an Automatic Threshold
Estimating the Crest Lines on Polygonal Mesh Models by an Automatic Threshold
AIRCC Publishing Corporation
 
IMPROVEMENTS OF THE ANALYSIS OF HUMAN ACTIVITY USING ACCELERATION RECORD OF E...
IMPROVEMENTS OF THE ANALYSIS OF HUMAN ACTIVITY USING ACCELERATION RECORD OF E...IMPROVEMENTS OF THE ANALYSIS OF HUMAN ACTIVITY USING ACCELERATION RECORD OF E...
IMPROVEMENTS OF THE ANALYSIS OF HUMAN ACTIVITY USING ACCELERATION RECORD OF E...
sipij
 
ESTIMATING THE CREST LINES ON POLYGONAL MESH MODELS BY AN AUTOMATIC THRESHOLD
ESTIMATING THE CREST LINES ON POLYGONAL MESH MODELS BY AN AUTOMATIC THRESHOLDESTIMATING THE CREST LINES ON POLYGONAL MESH MODELS BY AN AUTOMATIC THRESHOLD
ESTIMATING THE CREST LINES ON POLYGONAL MESH MODELS BY AN AUTOMATIC THRESHOLD
ijcsit
 
2019 cvpr paper overview by Ho Seong Lee
2019 cvpr paper overview by Ho Seong Lee2019 cvpr paper overview by Ho Seong Lee
2019 cvpr paper overview by Ho Seong Lee
Moazzem Hossain
 
2019 cvpr paper_overview
2019 cvpr paper_overview2019 cvpr paper_overview
2019 cvpr paper_overview
LEE HOSEONG
 
Scanners
Scanners Scanners
Scanners
ayesha455941
 
Cs8092 computer graphics and multimedia unit 3
Cs8092 computer graphics and multimedia unit 3Cs8092 computer graphics and multimedia unit 3
Cs8092 computer graphics and multimedia unit 3
SIMONTHOMAS S
 
Information theoritic analysis of entity dynamics on the linked open data cloud
Information theoritic analysis of entity dynamics on the linked open data cloudInformation theoritic analysis of entity dynamics on the linked open data cloud
Information theoritic analysis of entity dynamics on the linked open data cloud
MOVING Project
 
20110415 Scattering in CG and CV
20110415 Scattering in CG and CV20110415 Scattering in CG and CV
20110415 Scattering in CG and CV
Toru Tamaki
 
Medical Image Retrieval Based On Edge Histogram Descriptor
Medical Image Retrieval Based On Edge Histogram DescriptorMedical Image Retrieval Based On Edge Histogram Descriptor
Medical Image Retrieval Based On Edge Histogram Descriptor
inventionjournals
 
GRUPO 5 : novel fuzzy logic based edge detection technique
GRUPO 5 :  novel fuzzy logic based edge detection techniqueGRUPO 5 :  novel fuzzy logic based edge detection technique
GRUPO 5 : novel fuzzy logic based edge detection technique
viisonartificial2012
 
Lw3620362041
Lw3620362041Lw3620362041
Lw3620362041
IJERA Editor
 
Real life application of Enginneering mathematics
Real life application of Enginneering mathematicsReal life application of Enginneering mathematics
Real life application of Enginneering mathematics
Nasrin Rinky
 
Digital Classicist London Seminars 2013 - Seminar 6 (part 1) - Eleni Bozia
Digital Classicist London Seminars 2013 - Seminar 6 (part 1) - Eleni Bozia Digital Classicist London Seminars 2013 - Seminar 6 (part 1) - Eleni Bozia
Digital Classicist London Seminars 2013 - Seminar 6 (part 1) - Eleni Bozia
DigitalClassicistLondon
 
Image search engine
Image search engineImage search engine
Image search engine
Avanish Singh
 
Research on the characteristics and evaluation of nightscape along the LRT line
Research on the characteristics and evaluation of nightscape along the LRT lineResearch on the characteristics and evaluation of nightscape along the LRT line
Research on the characteristics and evaluation of nightscape along the LRT line
IJERA Editor
 
From Polygons to Quadratics.pptx
From Polygons to Quadratics.pptxFrom Polygons to Quadratics.pptx
From Polygons to Quadratics.pptx
yaswanthnaik27
 

Similar to 由點、線至面:從影像分析角度探討漫畫的組成與風格-朱威達 (20)

427lects
427lects427lects
427lects
 
Lecture1
Lecture1Lecture1
Lecture1
 
Semi-automatic Picture Book Generation based on Story Model and Agent-based S...
Semi-automatic Picture Book Generation based on Story Model and Agent-based S...Semi-automatic Picture Book Generation based on Story Model and Agent-based S...
Semi-automatic Picture Book Generation based on Story Model and Agent-based S...
 
Estimating the Crest Lines on Polygonal Mesh Models by an Automatic Threshold
Estimating the Crest Lines on Polygonal Mesh Models by an Automatic ThresholdEstimating the Crest Lines on Polygonal Mesh Models by an Automatic Threshold
Estimating the Crest Lines on Polygonal Mesh Models by an Automatic Threshold
 
IMPROVEMENTS OF THE ANALYSIS OF HUMAN ACTIVITY USING ACCELERATION RECORD OF E...
IMPROVEMENTS OF THE ANALYSIS OF HUMAN ACTIVITY USING ACCELERATION RECORD OF E...IMPROVEMENTS OF THE ANALYSIS OF HUMAN ACTIVITY USING ACCELERATION RECORD OF E...
IMPROVEMENTS OF THE ANALYSIS OF HUMAN ACTIVITY USING ACCELERATION RECORD OF E...
 
ESTIMATING THE CREST LINES ON POLYGONAL MESH MODELS BY AN AUTOMATIC THRESHOLD
ESTIMATING THE CREST LINES ON POLYGONAL MESH MODELS BY AN AUTOMATIC THRESHOLDESTIMATING THE CREST LINES ON POLYGONAL MESH MODELS BY AN AUTOMATIC THRESHOLD
ESTIMATING THE CREST LINES ON POLYGONAL MESH MODELS BY AN AUTOMATIC THRESHOLD
 
2019 cvpr paper overview by Ho Seong Lee
2019 cvpr paper overview by Ho Seong Lee2019 cvpr paper overview by Ho Seong Lee
2019 cvpr paper overview by Ho Seong Lee
 
2019 cvpr paper_overview
2019 cvpr paper_overview2019 cvpr paper_overview
2019 cvpr paper_overview
 
Scanners
Scanners Scanners
Scanners
 
Cs8092 computer graphics and multimedia unit 3
Cs8092 computer graphics and multimedia unit 3Cs8092 computer graphics and multimedia unit 3
Cs8092 computer graphics and multimedia unit 3
 
Information theoritic analysis of entity dynamics on the linked open data cloud
Information theoritic analysis of entity dynamics on the linked open data cloudInformation theoritic analysis of entity dynamics on the linked open data cloud
Information theoritic analysis of entity dynamics on the linked open data cloud
 
20110415 Scattering in CG and CV
20110415 Scattering in CG and CV20110415 Scattering in CG and CV
20110415 Scattering in CG and CV
 
Medical Image Retrieval Based On Edge Histogram Descriptor
Medical Image Retrieval Based On Edge Histogram DescriptorMedical Image Retrieval Based On Edge Histogram Descriptor
Medical Image Retrieval Based On Edge Histogram Descriptor
 
GRUPO 5 : novel fuzzy logic based edge detection technique
GRUPO 5 :  novel fuzzy logic based edge detection techniqueGRUPO 5 :  novel fuzzy logic based edge detection technique
GRUPO 5 : novel fuzzy logic based edge detection technique
 
Lw3620362041
Lw3620362041Lw3620362041
Lw3620362041
 
Real life application of Enginneering mathematics
Real life application of Enginneering mathematicsReal life application of Enginneering mathematics
Real life application of Enginneering mathematics
 
Digital Classicist London Seminars 2013 - Seminar 6 (part 1) - Eleni Bozia
Digital Classicist London Seminars 2013 - Seminar 6 (part 1) - Eleni Bozia Digital Classicist London Seminars 2013 - Seminar 6 (part 1) - Eleni Bozia
Digital Classicist London Seminars 2013 - Seminar 6 (part 1) - Eleni Bozia
 
Image search engine
Image search engineImage search engine
Image search engine
 
Research on the characteristics and evaluation of nightscape along the LRT line
Research on the characteristics and evaluation of nightscape along the LRT lineResearch on the characteristics and evaluation of nightscape along the LRT line
Research on the characteristics and evaluation of nightscape along the LRT line
 
From Polygons to Quadratics.pptx
From Polygons to Quadratics.pptxFrom Polygons to Quadratics.pptx
From Polygons to Quadratics.pptx
 

More from 台灣資料科學年會

[台灣人工智慧學校] 人工智慧技術發展與應用
[台灣人工智慧學校] 人工智慧技術發展與應用[台灣人工智慧學校] 人工智慧技術發展與應用
[台灣人工智慧學校] 人工智慧技術發展與應用
台灣資料科學年會
 
[台灣人工智慧學校] 執行長報告
[台灣人工智慧學校] 執行長報告[台灣人工智慧學校] 執行長報告
[台灣人工智慧學校] 執行長報告
台灣資料科學年會
 
[台灣人工智慧學校] 工業 4.0 與智慧製造的發展趨勢與挑戰
[台灣人工智慧學校] 工業 4.0 與智慧製造的發展趨勢與挑戰[台灣人工智慧學校] 工業 4.0 與智慧製造的發展趨勢與挑戰
[台灣人工智慧學校] 工業 4.0 與智慧製造的發展趨勢與挑戰
台灣資料科學年會
 
[台灣人工智慧學校] 開創台灣產業智慧轉型的新契機
[台灣人工智慧學校] 開創台灣產業智慧轉型的新契機[台灣人工智慧學校] 開創台灣產業智慧轉型的新契機
[台灣人工智慧學校] 開創台灣產業智慧轉型的新契機
台灣資料科學年會
 
[台灣人工智慧學校] 開創台灣產業智慧轉型的新契機
[台灣人工智慧學校] 開創台灣產業智慧轉型的新契機[台灣人工智慧學校] 開創台灣產業智慧轉型的新契機
[台灣人工智慧學校] 開創台灣產業智慧轉型的新契機
台灣資料科學年會
 
[台灣人工智慧學校] 台北總校第三期結業典禮 - 執行長談話
[台灣人工智慧學校] 台北總校第三期結業典禮 - 執行長談話[台灣人工智慧學校] 台北總校第三期結業典禮 - 執行長談話
[台灣人工智慧學校] 台北總校第三期結業典禮 - 執行長談話
台灣資料科學年會
 
[TOxAIA台中分校] AI 引爆新工業革命,智慧機械首都台中轉型論壇
[TOxAIA台中分校] AI 引爆新工業革命,智慧機械首都台中轉型論壇[TOxAIA台中分校] AI 引爆新工業革命,智慧機械首都台中轉型論壇
[TOxAIA台中分校] AI 引爆新工業革命,智慧機械首都台中轉型論壇
台灣資料科學年會
 
[TOxAIA台中分校] 2019 台灣數位轉型 與產業升級趨勢觀察
[TOxAIA台中分校] 2019 台灣數位轉型 與產業升級趨勢觀察 [TOxAIA台中分校] 2019 台灣數位轉型 與產業升級趨勢觀察
[TOxAIA台中分校] 2019 台灣數位轉型 與產業升級趨勢觀察
台灣資料科學年會
 
[TOxAIA台中分校] 智慧製造成真! 產線導入AI的致勝關鍵
[TOxAIA台中分校] 智慧製造成真! 產線導入AI的致勝關鍵[TOxAIA台中分校] 智慧製造成真! 產線導入AI的致勝關鍵
[TOxAIA台中分校] 智慧製造成真! 產線導入AI的致勝關鍵
台灣資料科學年會
 
[台灣人工智慧學校] 從經濟學看人工智慧產業應用
[台灣人工智慧學校] 從經濟學看人工智慧產業應用[台灣人工智慧學校] 從經濟學看人工智慧產業應用
[台灣人工智慧學校] 從經濟學看人工智慧產業應用
台灣資料科學年會
 
[台灣人工智慧學校] 台中分校第二期開學典禮 - 執行長報告
[台灣人工智慧學校] 台中分校第二期開學典禮 - 執行長報告[台灣人工智慧學校] 台中分校第二期開學典禮 - 執行長報告
[台灣人工智慧學校] 台中分校第二期開學典禮 - 執行長報告
台灣資料科學年會
 
台灣人工智慧學校成果發表會
台灣人工智慧學校成果發表會台灣人工智慧學校成果發表會
台灣人工智慧學校成果發表會
台灣資料科學年會
 
[台中分校] 第一期結業典禮 - 執行長談話
[台中分校] 第一期結業典禮 - 執行長談話[台中分校] 第一期結業典禮 - 執行長談話
[台中分校] 第一期結業典禮 - 執行長談話
台灣資料科學年會
 
[TOxAIA新竹分校] 工業4.0潛力新應用! 多模式對話機器人
[TOxAIA新竹分校] 工業4.0潛力新應用! 多模式對話機器人[TOxAIA新竹分校] 工業4.0潛力新應用! 多模式對話機器人
[TOxAIA新竹分校] 工業4.0潛力新應用! 多模式對話機器人
台灣資料科學年會
 
[TOxAIA新竹分校] AI整合是重點! 竹科的關鍵轉型思維
[TOxAIA新竹分校] AI整合是重點! 竹科的關鍵轉型思維[TOxAIA新竹分校] AI整合是重點! 竹科的關鍵轉型思維
[TOxAIA新竹分校] AI整合是重點! 竹科的關鍵轉型思維
台灣資料科學年會
 
[TOxAIA新竹分校] 2019 台灣數位轉型與產業升級趨勢觀察
[TOxAIA新竹分校] 2019 台灣數位轉型與產業升級趨勢觀察[TOxAIA新竹分校] 2019 台灣數位轉型與產業升級趨勢觀察
[TOxAIA新竹分校] 2019 台灣數位轉型與產業升級趨勢觀察
台灣資料科學年會
 
[TOxAIA新竹分校] 深度學習與Kaggle實戰
[TOxAIA新竹分校] 深度學習與Kaggle實戰[TOxAIA新竹分校] 深度學習與Kaggle實戰
[TOxAIA新竹分校] 深度學習與Kaggle實戰
台灣資料科學年會
 
[台灣人工智慧學校] Bridging AI to Precision Agriculture through IoT
[台灣人工智慧學校] Bridging AI to Precision Agriculture through IoT[台灣人工智慧學校] Bridging AI to Precision Agriculture through IoT
[台灣人工智慧學校] Bridging AI to Precision Agriculture through IoT
台灣資料科學年會
 
[2018 台灣人工智慧學校校友年會] 產業經驗分享: 如何用最少的訓練樣本,得到最好的深度學習影像分析結果,減少一半人力,提升一倍品質 / 李明達
[2018 台灣人工智慧學校校友年會] 產業經驗分享: 如何用最少的訓練樣本,得到最好的深度學習影像分析結果,減少一半人力,提升一倍品質 / 李明達[2018 台灣人工智慧學校校友年會] 產業經驗分享: 如何用最少的訓練樣本,得到最好的深度學習影像分析結果,減少一半人力,提升一倍品質 / 李明達
[2018 台灣人工智慧學校校友年會] 產業經驗分享: 如何用最少的訓練樣本,得到最好的深度學習影像分析結果,減少一半人力,提升一倍品質 / 李明達
台灣資料科學年會
 
[2018 台灣人工智慧學校校友年會] 啟動物聯網新關鍵 - 未來由你「喚」醒 / 沈品勳
[2018 台灣人工智慧學校校友年會] 啟動物聯網新關鍵 - 未來由你「喚」醒 / 沈品勳[2018 台灣人工智慧學校校友年會] 啟動物聯網新關鍵 - 未來由你「喚」醒 / 沈品勳
[2018 台灣人工智慧學校校友年會] 啟動物聯網新關鍵 - 未來由你「喚」醒 / 沈品勳
台灣資料科學年會
 

More from 台灣資料科學年會 (20)

[台灣人工智慧學校] 人工智慧技術發展與應用
[台灣人工智慧學校] 人工智慧技術發展與應用[台灣人工智慧學校] 人工智慧技術發展與應用
[台灣人工智慧學校] 人工智慧技術發展與應用
 
[台灣人工智慧學校] 執行長報告
[台灣人工智慧學校] 執行長報告[台灣人工智慧學校] 執行長報告
[台灣人工智慧學校] 執行長報告
 
[台灣人工智慧學校] 工業 4.0 與智慧製造的發展趨勢與挑戰
[台灣人工智慧學校] 工業 4.0 與智慧製造的發展趨勢與挑戰[台灣人工智慧學校] 工業 4.0 與智慧製造的發展趨勢與挑戰
[台灣人工智慧學校] 工業 4.0 與智慧製造的發展趨勢與挑戰
 
[台灣人工智慧學校] 開創台灣產業智慧轉型的新契機
[台灣人工智慧學校] 開創台灣產業智慧轉型的新契機[台灣人工智慧學校] 開創台灣產業智慧轉型的新契機
[台灣人工智慧學校] 開創台灣產業智慧轉型的新契機
 
[台灣人工智慧學校] 開創台灣產業智慧轉型的新契機
[台灣人工智慧學校] 開創台灣產業智慧轉型的新契機[台灣人工智慧學校] 開創台灣產業智慧轉型的新契機
[台灣人工智慧學校] 開創台灣產業智慧轉型的新契機
 
[台灣人工智慧學校] 台北總校第三期結業典禮 - 執行長談話
[台灣人工智慧學校] 台北總校第三期結業典禮 - 執行長談話[台灣人工智慧學校] 台北總校第三期結業典禮 - 執行長談話
[台灣人工智慧學校] 台北總校第三期結業典禮 - 執行長談話
 
[TOxAIA台中分校] AI 引爆新工業革命,智慧機械首都台中轉型論壇
[TOxAIA台中分校] AI 引爆新工業革命,智慧機械首都台中轉型論壇[TOxAIA台中分校] AI 引爆新工業革命,智慧機械首都台中轉型論壇
[TOxAIA台中分校] AI 引爆新工業革命,智慧機械首都台中轉型論壇
 
[TOxAIA台中分校] 2019 台灣數位轉型 與產業升級趨勢觀察
[TOxAIA台中分校] 2019 台灣數位轉型 與產業升級趨勢觀察 [TOxAIA台中分校] 2019 台灣數位轉型 與產業升級趨勢觀察
[TOxAIA台中分校] 2019 台灣數位轉型 與產業升級趨勢觀察
 
[TOxAIA台中分校] 智慧製造成真! 產線導入AI的致勝關鍵
[TOxAIA台中分校] 智慧製造成真! 產線導入AI的致勝關鍵[TOxAIA台中分校] 智慧製造成真! 產線導入AI的致勝關鍵
[TOxAIA台中分校] 智慧製造成真! 產線導入AI的致勝關鍵
 
[台灣人工智慧學校] 從經濟學看人工智慧產業應用
[台灣人工智慧學校] 從經濟學看人工智慧產業應用[台灣人工智慧學校] 從經濟學看人工智慧產業應用
[台灣人工智慧學校] 從經濟學看人工智慧產業應用
 
[台灣人工智慧學校] 台中分校第二期開學典禮 - 執行長報告
[台灣人工智慧學校] 台中分校第二期開學典禮 - 執行長報告[台灣人工智慧學校] 台中分校第二期開學典禮 - 執行長報告
[台灣人工智慧學校] 台中分校第二期開學典禮 - 執行長報告
 
台灣人工智慧學校成果發表會
台灣人工智慧學校成果發表會台灣人工智慧學校成果發表會
台灣人工智慧學校成果發表會
 
[台中分校] 第一期結業典禮 - 執行長談話
[台中分校] 第一期結業典禮 - 執行長談話[台中分校] 第一期結業典禮 - 執行長談話
[台中分校] 第一期結業典禮 - 執行長談話
 
[TOxAIA新竹分校] 工業4.0潛力新應用! 多模式對話機器人
[TOxAIA新竹分校] 工業4.0潛力新應用! 多模式對話機器人[TOxAIA新竹分校] 工業4.0潛力新應用! 多模式對話機器人
[TOxAIA新竹分校] 工業4.0潛力新應用! 多模式對話機器人
 
[TOxAIA新竹分校] AI整合是重點! 竹科的關鍵轉型思維
[TOxAIA新竹分校] AI整合是重點! 竹科的關鍵轉型思維[TOxAIA新竹分校] AI整合是重點! 竹科的關鍵轉型思維
[TOxAIA新竹分校] AI整合是重點! 竹科的關鍵轉型思維
 
[TOxAIA新竹分校] 2019 台灣數位轉型與產業升級趨勢觀察
[TOxAIA新竹分校] 2019 台灣數位轉型與產業升級趨勢觀察[TOxAIA新竹分校] 2019 台灣數位轉型與產業升級趨勢觀察
[TOxAIA新竹分校] 2019 台灣數位轉型與產業升級趨勢觀察
 
[TOxAIA新竹分校] 深度學習與Kaggle實戰
[TOxAIA新竹分校] 深度學習與Kaggle實戰[TOxAIA新竹分校] 深度學習與Kaggle實戰
[TOxAIA新竹分校] 深度學習與Kaggle實戰
 
[台灣人工智慧學校] Bridging AI to Precision Agriculture through IoT
[台灣人工智慧學校] Bridging AI to Precision Agriculture through IoT[台灣人工智慧學校] Bridging AI to Precision Agriculture through IoT
[台灣人工智慧學校] Bridging AI to Precision Agriculture through IoT
 
[2018 台灣人工智慧學校校友年會] 產業經驗分享: 如何用最少的訓練樣本,得到最好的深度學習影像分析結果,減少一半人力,提升一倍品質 / 李明達
[2018 台灣人工智慧學校校友年會] 產業經驗分享: 如何用最少的訓練樣本,得到最好的深度學習影像分析結果,減少一半人力,提升一倍品質 / 李明達[2018 台灣人工智慧學校校友年會] 產業經驗分享: 如何用最少的訓練樣本,得到最好的深度學習影像分析結果,減少一半人力,提升一倍品質 / 李明達
[2018 台灣人工智慧學校校友年會] 產業經驗分享: 如何用最少的訓練樣本,得到最好的深度學習影像分析結果,減少一半人力,提升一倍品質 / 李明達
 
[2018 台灣人工智慧學校校友年會] 啟動物聯網新關鍵 - 未來由你「喚」醒 / 沈品勳
[2018 台灣人工智慧學校校友年會] 啟動物聯網新關鍵 - 未來由你「喚」醒 / 沈品勳[2018 台灣人工智慧學校校友年會] 啟動物聯網新關鍵 - 未來由你「喚」醒 / 沈品勳
[2018 台灣人工智慧學校校友年會] 啟動物聯網新關鍵 - 未來由你「喚」醒 / 沈品勳
 

Recently uploaded

一比一原版(UCSF文凭证书)旧金山分校毕业证如何办理
一比一原版(UCSF文凭证书)旧金山分校毕业证如何办理一比一原版(UCSF文凭证书)旧金山分校毕业证如何办理
一比一原版(UCSF文凭证书)旧金山分校毕业证如何办理
nuttdpt
 
一比一原版巴斯大学毕业证(Bath毕业证书)学历如何办理
一比一原版巴斯大学毕业证(Bath毕业证书)学历如何办理一比一原版巴斯大学毕业证(Bath毕业证书)学历如何办理
一比一原版巴斯大学毕业证(Bath毕业证书)学历如何办理
y3i0qsdzb
 
4th Modern Marketing Reckoner by MMA Global India & Group M: 60+ experts on W...
4th Modern Marketing Reckoner by MMA Global India & Group M: 60+ experts on W...4th Modern Marketing Reckoner by MMA Global India & Group M: 60+ experts on W...
4th Modern Marketing Reckoner by MMA Global India & Group M: 60+ experts on W...
Social Samosa
 
办(uts毕业证书)悉尼科技大学毕业证学历证书原版一模一样
办(uts毕业证书)悉尼科技大学毕业证学历证书原版一模一样办(uts毕业证书)悉尼科技大学毕业证学历证书原版一模一样
办(uts毕业证书)悉尼科技大学毕业证学历证书原版一模一样
apvysm8
 
"Financial Odyssey: Navigating Past Performance Through Diverse Analytical Lens"
"Financial Odyssey: Navigating Past Performance Through Diverse Analytical Lens""Financial Odyssey: Navigating Past Performance Through Diverse Analytical Lens"
"Financial Odyssey: Navigating Past Performance Through Diverse Analytical Lens"
sameer shah
 
原版一比一利兹贝克特大学毕业证(LeedsBeckett毕业证书)如何办理
原版一比一利兹贝克特大学毕业证(LeedsBeckett毕业证书)如何办理原版一比一利兹贝克特大学毕业证(LeedsBeckett毕业证书)如何办理
原版一比一利兹贝克特大学毕业证(LeedsBeckett毕业证书)如何办理
wyddcwye1
 
UofT毕业证如何办理
UofT毕业证如何办理UofT毕业证如何办理
UofT毕业证如何办理
exukyp
 
一比一原版(UMN文凭证书)明尼苏达大学毕业证如何办理
一比一原版(UMN文凭证书)明尼苏达大学毕业证如何办理一比一原版(UMN文凭证书)明尼苏达大学毕业证如何办理
一比一原版(UMN文凭证书)明尼苏达大学毕业证如何办理
nyfuhyz
 
一比一原版(GWU,GW文凭证书)乔治·华盛顿大学毕业证如何办理
一比一原版(GWU,GW文凭证书)乔治·华盛顿大学毕业证如何办理一比一原版(GWU,GW文凭证书)乔治·华盛顿大学毕业证如何办理
一比一原版(GWU,GW文凭证书)乔治·华盛顿大学毕业证如何办理
bopyb
 
在线办理(英国UCA毕业证书)创意艺术大学毕业证在读证明一模一样
在线办理(英国UCA毕业证书)创意艺术大学毕业证在读证明一模一样在线办理(英国UCA毕业证书)创意艺术大学毕业证在读证明一模一样
在线办理(英国UCA毕业证书)创意艺术大学毕业证在读证明一模一样
v7oacc3l
 
Module 1 ppt BIG DATA ANALYTICS_NOTES FOR MCA
Module 1 ppt BIG DATA ANALYTICS_NOTES FOR MCAModule 1 ppt BIG DATA ANALYTICS_NOTES FOR MCA
Module 1 ppt BIG DATA ANALYTICS_NOTES FOR MCA
yuvarajkumar334
 
一比一原版(UCSB文凭证书)圣芭芭拉分校毕业证如何办理
一比一原版(UCSB文凭证书)圣芭芭拉分校毕业证如何办理一比一原版(UCSB文凭证书)圣芭芭拉分校毕业证如何办理
一比一原版(UCSB文凭证书)圣芭芭拉分校毕业证如何办理
nuttdpt
 
一比一原版(UO毕业证)渥太华大学毕业证如何办理
一比一原版(UO毕业证)渥太华大学毕业证如何办理一比一原版(UO毕业证)渥太华大学毕业证如何办理
一比一原版(UO毕业证)渥太华大学毕业证如何办理
bmucuha
 
一比一原版(Unimelb毕业证书)墨尔本大学毕业证如何办理
一比一原版(Unimelb毕业证书)墨尔本大学毕业证如何办理一比一原版(Unimelb毕业证书)墨尔本大学毕业证如何办理
一比一原版(Unimelb毕业证书)墨尔本大学毕业证如何办理
xclpvhuk
 
一比一原版兰加拉学院毕业证(Langara毕业证书)学历如何办理
一比一原版兰加拉学院毕业证(Langara毕业证书)学历如何办理一比一原版兰加拉学院毕业证(Langara毕业证书)学历如何办理
一比一原版兰加拉学院毕业证(Langara毕业证书)学历如何办理
hyfjgavov
 
Palo Alto Cortex XDR presentation .......
Palo Alto Cortex XDR presentation .......Palo Alto Cortex XDR presentation .......
Palo Alto Cortex XDR presentation .......
Sachin Paul
 
DSSML24_tspann_CodelessGenerativeAIPipelines
DSSML24_tspann_CodelessGenerativeAIPipelinesDSSML24_tspann_CodelessGenerativeAIPipelines
DSSML24_tspann_CodelessGenerativeAIPipelines
Timothy Spann
 
一比一原版英属哥伦比亚大学毕业证(UBC毕业证书)学历如何办理
一比一原版英属哥伦比亚大学毕业证(UBC毕业证书)学历如何办理一比一原版英属哥伦比亚大学毕业证(UBC毕业证书)学历如何办理
一比一原版英属哥伦比亚大学毕业证(UBC毕业证书)学历如何办理
z6osjkqvd
 
Challenges of Nation Building-1.pptx with more important
Challenges of Nation Building-1.pptx with more importantChallenges of Nation Building-1.pptx with more important
Challenges of Nation Building-1.pptx with more important
Sm321
 
Intelligence supported media monitoring in veterinary medicine
Intelligence supported media monitoring in veterinary medicineIntelligence supported media monitoring in veterinary medicine
Intelligence supported media monitoring in veterinary medicine
AndrzejJarynowski
 

Recently uploaded (20)

一比一原版(UCSF文凭证书)旧金山分校毕业证如何办理
一比一原版(UCSF文凭证书)旧金山分校毕业证如何办理一比一原版(UCSF文凭证书)旧金山分校毕业证如何办理
一比一原版(UCSF文凭证书)旧金山分校毕业证如何办理
 
一比一原版巴斯大学毕业证(Bath毕业证书)学历如何办理
一比一原版巴斯大学毕业证(Bath毕业证书)学历如何办理一比一原版巴斯大学毕业证(Bath毕业证书)学历如何办理
一比一原版巴斯大学毕业证(Bath毕业证书)学历如何办理
 
4th Modern Marketing Reckoner by MMA Global India & Group M: 60+ experts on W...
4th Modern Marketing Reckoner by MMA Global India & Group M: 60+ experts on W...4th Modern Marketing Reckoner by MMA Global India & Group M: 60+ experts on W...
4th Modern Marketing Reckoner by MMA Global India & Group M: 60+ experts on W...
 
办(uts毕业证书)悉尼科技大学毕业证学历证书原版一模一样
办(uts毕业证书)悉尼科技大学毕业证学历证书原版一模一样办(uts毕业证书)悉尼科技大学毕业证学历证书原版一模一样
办(uts毕业证书)悉尼科技大学毕业证学历证书原版一模一样
 
"Financial Odyssey: Navigating Past Performance Through Diverse Analytical Lens"
"Financial Odyssey: Navigating Past Performance Through Diverse Analytical Lens""Financial Odyssey: Navigating Past Performance Through Diverse Analytical Lens"
"Financial Odyssey: Navigating Past Performance Through Diverse Analytical Lens"
 
原版一比一利兹贝克特大学毕业证(LeedsBeckett毕业证书)如何办理
原版一比一利兹贝克特大学毕业证(LeedsBeckett毕业证书)如何办理原版一比一利兹贝克特大学毕业证(LeedsBeckett毕业证书)如何办理
原版一比一利兹贝克特大学毕业证(LeedsBeckett毕业证书)如何办理
 
UofT毕业证如何办理
UofT毕业证如何办理UofT毕业证如何办理
UofT毕业证如何办理
 
一比一原版(UMN文凭证书)明尼苏达大学毕业证如何办理
一比一原版(UMN文凭证书)明尼苏达大学毕业证如何办理一比一原版(UMN文凭证书)明尼苏达大学毕业证如何办理
一比一原版(UMN文凭证书)明尼苏达大学毕业证如何办理
 
一比一原版(GWU,GW文凭证书)乔治·华盛顿大学毕业证如何办理
一比一原版(GWU,GW文凭证书)乔治·华盛顿大学毕业证如何办理一比一原版(GWU,GW文凭证书)乔治·华盛顿大学毕业证如何办理
一比一原版(GWU,GW文凭证书)乔治·华盛顿大学毕业证如何办理
 
在线办理(英国UCA毕业证书)创意艺术大学毕业证在读证明一模一样
在线办理(英国UCA毕业证书)创意艺术大学毕业证在读证明一模一样在线办理(英国UCA毕业证书)创意艺术大学毕业证在读证明一模一样
在线办理(英国UCA毕业证书)创意艺术大学毕业证在读证明一模一样
 
Module 1 ppt BIG DATA ANALYTICS_NOTES FOR MCA
Module 1 ppt BIG DATA ANALYTICS_NOTES FOR MCAModule 1 ppt BIG DATA ANALYTICS_NOTES FOR MCA
Module 1 ppt BIG DATA ANALYTICS_NOTES FOR MCA
 
一比一原版(UCSB文凭证书)圣芭芭拉分校毕业证如何办理
一比一原版(UCSB文凭证书)圣芭芭拉分校毕业证如何办理一比一原版(UCSB文凭证书)圣芭芭拉分校毕业证如何办理
一比一原版(UCSB文凭证书)圣芭芭拉分校毕业证如何办理
 
一比一原版(UO毕业证)渥太华大学毕业证如何办理
一比一原版(UO毕业证)渥太华大学毕业证如何办理一比一原版(UO毕业证)渥太华大学毕业证如何办理
一比一原版(UO毕业证)渥太华大学毕业证如何办理
 
一比一原版(Unimelb毕业证书)墨尔本大学毕业证如何办理
一比一原版(Unimelb毕业证书)墨尔本大学毕业证如何办理一比一原版(Unimelb毕业证书)墨尔本大学毕业证如何办理
一比一原版(Unimelb毕业证书)墨尔本大学毕业证如何办理
 
一比一原版兰加拉学院毕业证(Langara毕业证书)学历如何办理
一比一原版兰加拉学院毕业证(Langara毕业证书)学历如何办理一比一原版兰加拉学院毕业证(Langara毕业证书)学历如何办理
一比一原版兰加拉学院毕业证(Langara毕业证书)学历如何办理
 
Palo Alto Cortex XDR presentation .......
Palo Alto Cortex XDR presentation .......Palo Alto Cortex XDR presentation .......
Palo Alto Cortex XDR presentation .......
 
DSSML24_tspann_CodelessGenerativeAIPipelines
DSSML24_tspann_CodelessGenerativeAIPipelinesDSSML24_tspann_CodelessGenerativeAIPipelines
DSSML24_tspann_CodelessGenerativeAIPipelines
 
一比一原版英属哥伦比亚大学毕业证(UBC毕业证书)学历如何办理
一比一原版英属哥伦比亚大学毕业证(UBC毕业证书)学历如何办理一比一原版英属哥伦比亚大学毕业证(UBC毕业证书)学历如何办理
一比一原版英属哥伦比亚大学毕业证(UBC毕业证书)学历如何办理
 
Challenges of Nation Building-1.pptx with more important
Challenges of Nation Building-1.pptx with more importantChallenges of Nation Building-1.pptx with more important
Challenges of Nation Building-1.pptx with more important
 
Intelligence supported media monitoring in veterinary medicine
Intelligence supported media monitoring in veterinary medicineIntelligence supported media monitoring in veterinary medicine
Intelligence supported media monitoring in veterinary medicine
 

由點、線至面:從影像分析角度探討漫畫的組成與風格-朱威達

  • 2. Fair Use Declaration • This statement is submitted for elaborating the legitimate status for illustrating all the “Screen Printings” and “Comics” in the “由點、線至面:從影像分析角度探討漫畫的組成與風格” are cited under the doctrine of “Fair Use” for research purpose if copyright protection applies on them. • The legal doctrine establishes globally that originality is needed to be seen for a work pursuing copyright protection, namely, the originality is the very essence of creation in intellectual domain. On account of that, an automatically recorded screen motion of the interactive computer games can be deemed as no copyright protection on it, therefore it can be lawfully applied in the “由點、線至面:從影像分析角度探討漫畫的組成與風格” as part of the research materials without the written permission from the copyright owner of the computer games. However, some people might treat them as copyright protected materials still for the drawings or similar creations in the background of the animations or comics, if that applies, according to the international intellectual property agreements and copyright law in respective jurisdictions, such as Agreement on Trade-Related Aspects of Intellectual Property Rights (TRIPS) article 13, Berne Convention for the Protection of Literary and Artistic Works article 9(2), EU Copyright Directive article 5(5), Copyright Law of the United States of America section 107 and Taiwan Copyright Act article 65, the Fair Use and Fair Dealing of a copyrighted work based on teaching, scholarship, or research shall applied under the circumstances to sustain the citation for all the “Screen Printings“ and “Comics” in the “由點、線至面:從影像分析角度探討漫畫的組成與風格” as legitimate action abided by at law, which do not conflict with a normal exploitation of the works and do not unreasonably prejudice the legitimate interests of the right holders. 2
  • 3. Introduction • Comics-based presentation for movie, animation, and photos, emerges recently. • Comics are believed to be an ideal medium for visual storytelling because of rich expressivity, high interactivity, and high portability. 3 Sample generated comic pages from the animation “Neon Genesis Evangelion” (top) and from the animation “Summer Wars” (bottom).
  • 4. Introduction Three key constituents of manga [1]. 1. Drawing/絵絵絵絵 2. Language/言葉言葉言葉言葉 3. Panel/コマコマコマコマ 4[1] 夏目 房之介 (1997). マンガはなぜ面白いのか―その表現と文法. NHKライブラリー. 點 線 面 Drawing Panel
  • 5. Outline • Part 1: Manga Style Analysis • Part 2: Comics-based Storytelling 5
  • 6. Motivation • As the internet and mobile devices become popular, digital mangas are widely accessible. • Different mangas may have different styles. We focus on which features can be used to distinguish different manga styles. 6
  • 7. From bounding box of each panel, we extract features to describe characteristics of layout. 1) : average panel height (derived from bounding boxes) 2) : average panel width 3) : standard deviation of 4) : standard deviation of 7 Panel Feature Extraction
  • 8. 5) : the ratio of total panel area to the whole page 6) : average panel area 7) : standard deviation of 8) : average slope of vertical panel boundaries 9) : average slope of horizontal panel boundaries 10) : standard deviation of 11) : standard deviation of 8 Panel Feature Extraction
  • 9. 9 Panel Feature Extraction Top row: sample manga pages from three different artists. Bottom row: panel feature distributions corresponding to these pages.
  • 10. Screentone Detection 11 • Screentone is a technique for applying textures and shades to drawings, used as an alternative to hatching. • Different authors have different habits to use screentone.
  • 11. Screentone Detection 11 1. Image binarization. 2. Dilation. 3. Delete small areas. 4. Get screentone areas. 5. Extract patches from screentone areas.
  • 12. Screentone Feature Extraction 12 • Two screentone features are proposed: – The ratio of screentone areas to the whole panel area ( ). – Bag of screentone ( ). • Gabor wavelet texture • Use affinity propagation to cluster features, and use the bag of word model to describe screentone. B.J. Frey and D. Dueck. Clustering by passing messages between data points. Science, 2007.
  • 13. Screentone Feature Extraction 13 Top row: sample manga pages from three different artists. Bottom row: the BoP distributions corresponding to these artists.
  • 14. Character Detection 14 • Apply the eye detection model in a sliding window manner to detect eyes. • Expand the areas from eye regions. The big regions extended by all detected eye regions are then covered by a minimum bounding box, which is finally the determined character’s head region.
  • 15. Line Feature Extraction 15 • Canny edge detection • Edge linking P. Kovesi, School of Computer Science & Software Engineering, The University of Western Australia, http://www.csse.uwa.edu.au, 2001. (1) Face image (2) Canny edge image (3) Edge linking (4) Straight line segmentation.
  • 16. Line Feature Extraction 16 • Included angle between lines ( ): For two spatially adjacent segment lines, we calculate the included angle between them. The feature can be represented as a 12-dimensional histogram. Shonen Shojo
  • 17. Line Feature Extraction • Line orientation ( ): Orientation of a line segment is defined as the included angle between it and the horizontal axis. The feature can be represented as a 12-dimensional orientation histogram. 17 Mitsuru Adachi Terajima Yuji
  • 18. Line Feature Extraction 18 • Density of line segments ( ): We calculate the number of lines in its neighborhood, and the information over all line segments are gathered to form the feature. It can be represented by 20-dimensional histogram. Mitsuru Adachi Terajima Yuji
  • 19. Line Feature Extraction 19 • Orientation of nearby lines ( ): Orientations of a line segment’s nearby lines are calculated, in the representation of a 12-dimensional orientation histogram Mitsuru Adachi Terajima Yuji
  • 20. Line Feature Extraction • Number of nearby lines with similar orientation ( ): To a line segment L, we calculate the number of its nearby lines that have similar orientation to L. Such information over all line segments is gathered to form a 20-dimensional histogram. 20 Shonen Shojo
  • 21. Line Feature Extraction 21 • Line strength varied ( ): We use twenty different threshold settings for Canny edge detection. The ratio of detection results to standard result is the feature. It is a 20- dimensional vector . Shonen Shojo
  • 22. Feature Analysis 23 • Comparison between mangas of different types of magazines. Shone manga: 3 different mangas, totally 300 pages. Shojo manga: 3 different mangas, totally 300 pages. (4) “ I love flowers and Mr.”, Kumaoka Fuyuyu. (5) “ The first love honey”, Minase Ai. (6) “ From me to you”, Shiina Karuho. (1) “Nisekoi”, Komi Naoshi. (2) “ Yamada-kun and the seven witches”, Miki Yoshikawa. (3) “ Agatsuma's my daughter”, Nishikida Keikokorozashi.
  • 23. Feature Analysis 23 – Comparison between mangas with the same topic but drawn by different artists. – Use statistical comparison to analyze the proposed features. Baseball manga: 3 different mangas, totally 300 pages. (1) “Ace of Diamond”, Terajima Yuji. (2) “Mix”, Mitsuru Adachi. (3) “Big Windup”, Mizushima Tsutomu.
  • 24. Feature Analysis 24 – Comparison between mangas of different types of magazines. P-value 0.039 0.414 0.151 0.429 0.017 0.003 0.044 0.000 Shonen Shojo
  • 25. Feature Analysis 25 • Distance map (Shonen mangas v.s Shojo mangas): ( : 0.017) ( : 0.003) ( : 0.414) ( : 0.429) shonen shonen shojo shojo
  • 26. Feature Analysis 26 – Comparison between mangas with the same topic but drawn by different artists. – P-value: TY v.s MA 0.037 0.183 0.000 0.277 0.000 0.000 0.6 0.000 TY v.s MT 0.105 0.006 0.075 0.007 0.199 0.074 0.47 0.000 MA v.s MT 0.325 0.091 0.161 0.061 0.011 0.000 0.14 0.000 Terajima Yuji (TY) Mitsuru Adachi (MA) Mizuhima Tsutomu (MT)
  • 27. Feature Analysis 27 • Spider chart (based on skewness of features):
  • 28. Feature Analysis 34 • Comparison between mangas of different types of magzines. – SVM test: 5-fold cross-validation. – Comparison between mangas with the same topic but drawn by different artists. – SVM test: 5-fold cross-validation accuracy 71.6 61.5 60.5 56.8 70.3 74.5 82 75 79.3 80 TY v.s MA 74.2 64.2 70 62.1 77.8 90.7 90 63.3 71.6 72 TY v.s MT 65 72.8 62.8 72.8 50 69.2 76.1 56.6 88 88 MA v.s MT 71.4 67.1 64.2 68.5 74.2 86.4 86.1 66.6 82 81
  • 29. Latent Style Model • Developing a style model based on Latent Dirichlet Allocation (LDA) to discover style elements. • Documents can be represented as mixtures of latent topics, where each topic is formed by a distribution over words. 29 …… 1 2 3 Document Topic Word ~ ~ , , Blei, D. M., Ng, A. Y., & Jordan, M. I. (2003). Latent dirichlet allocation. Journal of Machine Learning Research, 3, 993-1022.
  • 30. Latent Style Model 30 Attribute of Latent Dirichlet Allocation Text document Latent topics Word Attribute of Latent Style Model Manga pages of the same artist Latent style elements Visual word (manga page) Given a set of documents , … , ! with the observed visual words, we can efficiently learn the model by the Gibbs sampling algorithm. Style probabilities of a document can be estimated, which enable us to represent a document as a distribution of style elements.
  • 31. 31 Style Element Distributions Top: sample manga pages from three different documents. Bottom: style element distributions corresponding to these documents.
  • 32. Artists in Dataset 1 32 (F)“天地を喰らう”,本宮 ひろ志. (G)“北斗の拳”,原 哲夫. (H)“魁!!男塾”,宮下 あきら. (C) “うしおととら”,藤田 和日郎. (D)“金色のガッシュ!!”,雷句 誠. (E)“呪法解禁!!”,麻生 羽呂. (A)“Fairy Tail”,真島 ヒロ. (B) “ヤンキー君とメガネちゃん”,吉河 美希. (A) (B) (D)(C) (E) (F) (G) (H) 100 manga pages from eight different artists, consisting of totally 800 manga pages.
  • 33. Art Movement in Dataset 1 33
  • 34. 34 (B) “ヤンキー君とメガネちゃん” 吉河 美希. (E) “呪法解禁!!” 麻生 羽呂. (G)“北斗の拳” 原 哲夫. Artist Style Element Distributions Top: sample manga pages from three different artists. Bottom: style element distributions corresponding to these artists.
  • 35. Style-Based Art Movement Retrieval 35 Given a query, we would like to retrieve manga documents produced by artists of the same movement. 0.65 0.7 0.75 0.8 0.85 0.9 10 styles 20 styles 30 styles 40 styles MAP@10 hist. intersection(line features) chi-square(line features) hist. intersection(all features) chi-square(all features) distance measure 10 styles 20 styles 30 styles 40 styles line features histogram intersection 0.7093 0.7152 0.7329 0.7158 line features chi square 0.7024 0.719 0.7443 0.7383 all features histogram intersection 0.8413 0.8472 0.8483 0.8125 all features chi square 0.8358 0.8518 0.8544 0.8196 MAP@10
  • 36. Style-Based Artist Retrieval 36 Given an artist’s manga document, we would like to retrieve other documents produced by the same artist. 0.55 0.6 0.65 0.7 0.75 0.8 0.85 10 styles 20 styles 30 styles 40 styles MAP@10 hist. intersection(line features) chi-square(line features) hist. intersection(all features) chi-square(all features) distance measure 10 styles 20 styles 30 styles 40 styles line features histogram intersection 0.6401 0.6404 0.6460 0.6323 line features chi square 0.6385 0.6457 0.6541 0.6537 all features histogram intersection 0.7627 0.7663 0.7854 0.7654 all features chi square 0.7470 0.7553 0.7939 0.7824 MAP@10
  • 37. Artwork Period Retrieval We take the manga JoJo's Bizarre Adventure for analysis, which is created by Hirohiko Araki from 1987 to now. Totally 300 pages. 37 ジョジョの奇妙な冒険 Part 3 (1989-1992) ジョジョの奇妙な冒険 Part 8 (2011-ongoing) ジョジョの奇妙な冒険 Part 1 (1987)
  • 38. Sample results of the query and top returned documents. 38 Artwork Period Retrieval
  • 39. 39 Given an artist’s manga document, we would like to retrieve other documents produced by the same period. 0.5 0.55 0.6 0.65 0.7 0.75 10 styles 20 styles 30 styles 40 styles MAP@10 hist. intersection(line features) chi-square(line features) hist. intersection(all features) chi-square(all features) distance measure 10 styles 20 styles 30 styles 40 styles line features histogram intersection 0.5703 0.6247 0.6377 0.6428 line features chi square 0.5779 0.6446 0.6581 0.6622 all features histogram intersection 0.6321 0.6521 0.6698 0.6751 all features chi square 0.6376 0.6641 0.6781 0.6899 MAP@10 Artwork Period Retrieval
  • 40. Summary • Manga style analysis – Manga-specific features – Based on LDA, implicit style elements are discovered in a probabilistic framework. – Analysis can be achieved at the style level rather than the feature level. • Applications – Style-based browsing – Influence discovery – Relationship between style and other properties 40
  • 41. Part 2: Comics-Based Storytelling 朱威達 中正大學資訊工程學系 wtchu@ccu.edu.tw 41
  • 42. Comics-Based Storytelling • Goal: Develop a systematic framework to enable comics-based storytelling of temporal image sequences – Comic design theory – Formulate core components as optimization problems and systematically solve them – Interactivity 42
  • 43. Challenges • Q1. How to segment the given temporal image sequence, so that images in the same subsequence present similar semantics/events/scenes and are appropriately to be put into the same comic page? 43
  • 44. Challenges • Q2. What is the best layout to arrange panels in the same page? 44 ?? ?
  • 45. Challenges • Q3. How to place speech balloons, so that important content in images are not occluded by balloons, and balloons’ positions direct viewer’s gaze to build a pleasing reading trajectory? 45
  • 46. Optimized Page Allocation • Allocate appropriate number of comic pages that may include various numbers of cells. – Visual coherence: Consecutive or similar visual content tends to be put into the same comic page. – Browsing pace: Keyframes conveying high motion are tended to be put into the same pages containing more panels to build tense browsing experience. • A labeling problem, with the temporal continuity constraint – Solution: Genetic algorithm (GA) 46 1 1 1 2 2 2 2 3 3 4 4 4 Q1. How to segment the given temporal image sequence?
  • 47. Optimized Page Allocation 47 1 1 1 2 2 2 2 3 3 4 4 4
  • 48. Objective Function (Fitness) Page 1 Page 2 Page 3 Page 1 Page 2 Page 1 Page 2 At the 5th iteration At the 20th iteration At the 90th iteration 0.7 0.75 0.8 0.85 0.9 0.95 1 11 21 31 41 51 61 71 81 91 101 Best Average Worst 5th iteration 20th iteration 90th iteration 48 Iteration fitness
  • 49. Optimized Layout Selection • Desired properties – More important images should be allocated larger panels – Keyframes extracted from the same shot or photos consecutively taken in the same place are better to be put in the same row of panels – Keyframes with more subtitle words or photos with more annotation are to be allocated larger panels. • Idea – Determine the images-layout pair that has the most similar “importance” distributions. 49 Q2. What is the best layout to arrange panels in the same page?
  • 50. Image Importance • From each keyframe, the region of interest (ROI) is extracted based on color contrast [Cheng’11]. • Assume that the keyframes are determined to put at the same page. The importance value of a keyframe is defined as ratio of the area of ROI ratio of the number of subtitle words the minimum color histogram distance from this frame to other frames 50 M.-M. Cheng, G.-X. Zhang, N.J. Mitra, X. Huang, and S.-M. Hu. “Global contrast based salient region detection.” Proc. of IEEE Conference on Computer Vision and Pattern Recognition, pp. 409-416, 2011.
  • 51. Layout Design 51 ... ... ... ......... 1 panel layout 2 panels layout 3 panels layout 4 panels layout 5 panel layout 6 panels layout 7 panels layout 8 panels layout
  • 52. Layout Importance • Layout importance • To measure how appropriately a layout matches with the given image sequence – Inner product: 52 1/3 1/3 1/3 0.5 0.25 0.25 0.25 0.25 0.5 . . . . . . . . : the ratio of the area of the jth panel to the area of the whole page.
  • 53. Layout Importance • Binary vectors to show how panels are arranged into rows – How different panel arrangements fit with shot: • Importance distribution in terms of numbers of spoken words – Inner product: 53 1st row 2nd row 3rd row 1st row 2nd row r1=(01100) r2=(00110) r3=(01000)
  • 54. 1/3 1/3 1/3 0.5 0.25 0.25 0.25 0.25 0.5 . . . . . . . . Layout Selection 54 r1=(011) r2=(010) r1=(001) Shot # 1 2 2 Images q 0 1 0 The best layout is selected by:
  • 56. Layout Selection Comparison 56 Example 2: Layout selected by the proposed method (c) and two different equally-allocated layouts (d)(e). Example 1: Layout selected by the proposed method (a) and by equal allocation (b). (a) (b) (c) (d) (e)
  • 57. Balloon Placement • Optimal positions are determined by jointly considering the following factors: – Balloons should not overlap with the regions of interest (ROIs) in images. – Balloons should be placed as close as the ROI in images. – When there are multiple balloons in a panel, the sentences spoken earlier should be placed closer to the left-top corner of the panel. This is to maintain correct reading order. – Balloons should not overlap with each other. – Reading trajectory should be built so that reading order is not only correct but also vivid. 57 Q3. How to place speech balloons?
  • 58. Optimized Speech Balloon Placement • Finally, the five factors are linearly combined: • This problem can be intuitively mapped to the one efficiently solved by the particle swarm optimization algorithm (PSO). 58 local region global region
  • 59. 59 Left: demonstration of PSO in 200 iterations Right: ROI of comic page Comparison of balloon placement considering different factors. (a)(c) The placement results if all factors are jointly considered. (b) The placement result if overlapping between balloons is not taken into account. (d) The placement result if overlapping between balloons and ROIs is not taken into account. Optimized Speech Balloon Placement
  • 61. Summary 61 • We have presented a system that automatically transforms temporal image sequences into comics-based storytelling. – Optimized page allocation – Optimized layout selection – Optimized speech balloon placement • Future work – ROI analysis techniques specially designed for animation – Investigation of semantics on automatic comics generation
  • 62. Questions? Wei-Ta Chu (朱威達) National Chung Cheng University wtchu@ccu.edu.tw 62