SlideShare a Scribd company logo
Who am I ?
M a c h i n e L e a r n i n g E n g i n e e r
A m i t K u s h w a h a
Image Aesthetics
W H A T D E F I N E S A N I M A G E ?
★ Image aesthetic evaluation aims to classify photos into high quality or low quality from the perspective
of human.
★ Many visual features have been explored under this formulation (handcrafted features), ranging from
low-level image statistics, such as edge distributions and color histograms, to high-level photographic
rules, such as the rule of thirds and golden ratio
Beautiful Capture
“ B E A U T Y I S R E A L L Y I N T H E E Y E O F T H E B E H O L D E R ”
✦ While everyone has different tastes, there are universally accepted
norms when it comes to beauty – things which everyone pretty
much agrees are beautiful, like sunsets or sunrises over the
mountains or the ocean.
A S U B J E C T I V E C O N J E C T U R E
T E C H N I Q U E S O F I M A G E C A P T U R I N G
A S U B J E C T I V E C O N J E C T U R E
✦ Image aesthetics can be affected by the different usages of
lighting, contrast , and image composition
Beautiful Capture
The Two Images
F A C T O R S L I K E L I G H T I N G , C O N T R A S T , A N G L E D E T E R M I N E T H E A E S T H E T I C S
Significance of Aesthetic
Assessment
✦ With the ever increasing user generated content, biggest challenge is to
showcase high quality images to users.
✦ Zomato measures the performance of restaurant for ad sales with click
through rate (CTR) as one of the parameter. Restaurants with High Quality
Display Image have greater CTR.
01
02
04
06
WRITESOMETHING
Photo Gallery
P H O T O S D O H A V E A S T O R Y
Let’s solve Image
Aesthetics with the
most disruptive
technology over the
last five years.
Deep Learning
S T A T E O F T H E A R T I N M A N Y F I E L D S N O W
Fixed Size Input
Constraint
D E E P M O D E L I N P U T L A Y E R
✦ This constraint of fixed size input in Deep Network
compromises the aesthetics of original image. input images
need to be transformed via cropping, scaling, or padding, which
often damages image composition, reduces image resolution,
or causes image distortion, thus compromising the aesthetics of
the original images.
Input Layer of Network
A M A Z I N G I N T H E I R O R I G I N A L A S P E C T R A T I O
Original Image
Transformed Image
R E S I Z I N G L O S E S T H E O R I G I N A L A E S T H E T I C S O F I M A G E
O R I G I N A L R E S I Z E D
Transformed Image
O R I G I N A L R E S I Z E D
R E S I Z I N G L O S E S T H E O R I G I N A L A E S T H E T I C S O F I M A G E
DEEP
LEARNING
Demystifying the Network
✦ The first few layers of networks are either convolution or pooling layer, followed by fully connected
layers.
✦ The fixed length input is only the constraint of fully-connected layer. Be it convolution or pooling,
both perform operations on input, with the spatial information.
Spatial Pyramid
Pooling
✦ Network with another pooling strategy, ‘spatial pyramid pooling’ just before the fully
connected layer, makes it capable of taking input of any size and generate fixed length
representation.
Max Pooling
O U T P U T I S P R O P O R T I O N A L T O I N P U T
Kernel size is fixed
Spatial Pyramid Pooling
Output dimension (Bin Size , Bin Size)
Spatial Pyramid Pooling
Fixed Bin Numbers
Fixed Kernel Size
SPP-Net
CNN
Training a SPP-net
Z O M A T O D A T A S E T U S E D
T R A I N I N G L O S S T R A I N I N G A C C U R A C Y
M A X - A C C U R A C Y - 7 7 . 2
NOREGIONOFINTEREST
Interesting Prediction Results
Spp-Score=0.46
REGIONOFINTERESTISPRESENT
Interesting Prediction Results
Spp-Score=0.94
It’s often neglected, but plays a major role in classification learning.
S C A L E I N V A R I A N T L E A R N I N G
Allows to explore CNN without the constraint of fixed size representation of input.
F I X E D S I Z E I N P U T
Take Aways
S P A T I A L P Y R A M I D P O O L I N G N E T
R E F E R E N C E S
✦ Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun, “Spatial Pyramid Pooling in Deep
Convolutional Networks for Visual Recognition”
✦ Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton, ImageNet Classification with Deep
Convolutional Neural Networks 2012
Composition-Preserving Deep Photo Aesthetics Assessment
✦ Long Mai, Hailin Jin, Feing Liu, Composition-Preserving Deep Photo Aesthetics
Assessment
h t t p s : / / w w w . g i t h u b . c o m / y a r d s t i c k 1 7 /
h t t p s : / / w w w . l i n k e d i n . c o m / i n / y a r d s t i c k 1 7 /
a m i t _ k u s h w a h a @ o u t l o o k . c o m
Thank You
F i n d m e h e r e

More Related Content

What's hot

Convolutional Neural Network (CNN) - image recognition
Convolutional Neural Network (CNN)  - image recognitionConvolutional Neural Network (CNN)  - image recognition
Convolutional Neural Network (CNN) - image recognition
YUNG-KUEI CHEN
 
Deep Learning for Computer Vision: Object Detection (UPC 2016)
Deep Learning for Computer Vision: Object Detection (UPC 2016)Deep Learning for Computer Vision: Object Detection (UPC 2016)
Deep Learning for Computer Vision: Object Detection (UPC 2016)
Universitat Politècnica de Catalunya
 
Machine Learning - Convolutional Neural Network
Machine Learning - Convolutional Neural NetworkMachine Learning - Convolutional Neural Network
Machine Learning - Convolutional Neural Network
Richard Kuo
 
Convolutional neural network
Convolutional neural networkConvolutional neural network
Convolutional neural network
MojammilHusain
 
Convolutional neural network
Convolutional neural networkConvolutional neural network
Convolutional neural network
Itachi SK
 
Convolutional Neural Network (CNN)
Convolutional Neural Network (CNN)Convolutional Neural Network (CNN)
Convolutional Neural Network (CNN)
Abdulrazak Zakieh
 
Transfer Learning and Fine-tuning Deep Neural Networks
 Transfer Learning and Fine-tuning Deep Neural Networks Transfer Learning and Fine-tuning Deep Neural Networks
Transfer Learning and Fine-tuning Deep Neural Networks
PyData
 
UNet-VGG16 with transfer learning for MRI-based brain tumor segmentation
UNet-VGG16 with transfer learning for MRI-based brain tumor segmentationUNet-VGG16 with transfer learning for MRI-based brain tumor segmentation
UNet-VGG16 with transfer learning for MRI-based brain tumor segmentation
TELKOMNIKA JOURNAL
 
AlexNet(ImageNet Classification with Deep Convolutional Neural Networks)
AlexNet(ImageNet Classification with Deep Convolutional Neural Networks)AlexNet(ImageNet Classification with Deep Convolutional Neural Networks)
AlexNet(ImageNet Classification with Deep Convolutional Neural Networks)
Fellowship at Vodafone FutureLab
 
YOLOv5 BASED WEB APPLICATION FOR INDIAN CURRENCY NOTE DETECTION
YOLOv5 BASED WEB APPLICATION FOR INDIAN CURRENCY NOTE DETECTIONYOLOv5 BASED WEB APPLICATION FOR INDIAN CURRENCY NOTE DETECTION
YOLOv5 BASED WEB APPLICATION FOR INDIAN CURRENCY NOTE DETECTION
IRJET Journal
 
Multiclass classification of imbalanced data
Multiclass classification of imbalanced dataMulticlass classification of imbalanced data
Multiclass classification of imbalanced data
SaurabhWani6
 
1.Introduction to deep learning
1.Introduction to deep learning1.Introduction to deep learning
1.Introduction to deep learning
KONGU ENGINEERING COLLEGE
 
Convolutional Neural Network - CNN | How CNN Works | Deep Learning Course | S...
Convolutional Neural Network - CNN | How CNN Works | Deep Learning Course | S...Convolutional Neural Network - CNN | How CNN Works | Deep Learning Course | S...
Convolutional Neural Network - CNN | How CNN Works | Deep Learning Course | S...
Simplilearn
 
Data Augmentation
Data AugmentationData Augmentation
Data Augmentation
Md Tajul Islam
 
PR-132: SSD: Single Shot MultiBox Detector
PR-132: SSD: Single Shot MultiBox DetectorPR-132: SSD: Single Shot MultiBox Detector
PR-132: SSD: Single Shot MultiBox Detector
Jinwon Lee
 
Convolutional neural network
Convolutional neural networkConvolutional neural network
Convolutional neural network
Ferdous ahmed
 
Introduction to Recurrent Neural Network
Introduction to Recurrent Neural NetworkIntroduction to Recurrent Neural Network
Introduction to Recurrent Neural Network
Yan Xu
 
"Semantic Segmentation for Scene Understanding: Algorithms and Implementation...
"Semantic Segmentation for Scene Understanding: Algorithms and Implementation..."Semantic Segmentation for Scene Understanding: Algorithms and Implementation...
"Semantic Segmentation for Scene Understanding: Algorithms and Implementation...
Edge AI and Vision Alliance
 
Introduction au Deep Learning
Introduction au Deep Learning Introduction au Deep Learning
Introduction au Deep Learning
Niji
 
Stereo Matching by Deep Learning
Stereo Matching by Deep LearningStereo Matching by Deep Learning
Stereo Matching by Deep Learning
Yu Huang
 

What's hot (20)

Convolutional Neural Network (CNN) - image recognition
Convolutional Neural Network (CNN)  - image recognitionConvolutional Neural Network (CNN)  - image recognition
Convolutional Neural Network (CNN) - image recognition
 
Deep Learning for Computer Vision: Object Detection (UPC 2016)
Deep Learning for Computer Vision: Object Detection (UPC 2016)Deep Learning for Computer Vision: Object Detection (UPC 2016)
Deep Learning for Computer Vision: Object Detection (UPC 2016)
 
Machine Learning - Convolutional Neural Network
Machine Learning - Convolutional Neural NetworkMachine Learning - Convolutional Neural Network
Machine Learning - Convolutional Neural Network
 
Convolutional neural network
Convolutional neural networkConvolutional neural network
Convolutional neural network
 
Convolutional neural network
Convolutional neural networkConvolutional neural network
Convolutional neural network
 
Convolutional Neural Network (CNN)
Convolutional Neural Network (CNN)Convolutional Neural Network (CNN)
Convolutional Neural Network (CNN)
 
Transfer Learning and Fine-tuning Deep Neural Networks
 Transfer Learning and Fine-tuning Deep Neural Networks Transfer Learning and Fine-tuning Deep Neural Networks
Transfer Learning and Fine-tuning Deep Neural Networks
 
UNet-VGG16 with transfer learning for MRI-based brain tumor segmentation
UNet-VGG16 with transfer learning for MRI-based brain tumor segmentationUNet-VGG16 with transfer learning for MRI-based brain tumor segmentation
UNet-VGG16 with transfer learning for MRI-based brain tumor segmentation
 
AlexNet(ImageNet Classification with Deep Convolutional Neural Networks)
AlexNet(ImageNet Classification with Deep Convolutional Neural Networks)AlexNet(ImageNet Classification with Deep Convolutional Neural Networks)
AlexNet(ImageNet Classification with Deep Convolutional Neural Networks)
 
YOLOv5 BASED WEB APPLICATION FOR INDIAN CURRENCY NOTE DETECTION
YOLOv5 BASED WEB APPLICATION FOR INDIAN CURRENCY NOTE DETECTIONYOLOv5 BASED WEB APPLICATION FOR INDIAN CURRENCY NOTE DETECTION
YOLOv5 BASED WEB APPLICATION FOR INDIAN CURRENCY NOTE DETECTION
 
Multiclass classification of imbalanced data
Multiclass classification of imbalanced dataMulticlass classification of imbalanced data
Multiclass classification of imbalanced data
 
1.Introduction to deep learning
1.Introduction to deep learning1.Introduction to deep learning
1.Introduction to deep learning
 
Convolutional Neural Network - CNN | How CNN Works | Deep Learning Course | S...
Convolutional Neural Network - CNN | How CNN Works | Deep Learning Course | S...Convolutional Neural Network - CNN | How CNN Works | Deep Learning Course | S...
Convolutional Neural Network - CNN | How CNN Works | Deep Learning Course | S...
 
Data Augmentation
Data AugmentationData Augmentation
Data Augmentation
 
PR-132: SSD: Single Shot MultiBox Detector
PR-132: SSD: Single Shot MultiBox DetectorPR-132: SSD: Single Shot MultiBox Detector
PR-132: SSD: Single Shot MultiBox Detector
 
Convolutional neural network
Convolutional neural networkConvolutional neural network
Convolutional neural network
 
Introduction to Recurrent Neural Network
Introduction to Recurrent Neural NetworkIntroduction to Recurrent Neural Network
Introduction to Recurrent Neural Network
 
"Semantic Segmentation for Scene Understanding: Algorithms and Implementation...
"Semantic Segmentation for Scene Understanding: Algorithms and Implementation..."Semantic Segmentation for Scene Understanding: Algorithms and Implementation...
"Semantic Segmentation for Scene Understanding: Algorithms and Implementation...
 
Introduction au Deep Learning
Introduction au Deep Learning Introduction au Deep Learning
Introduction au Deep Learning
 
Stereo Matching by Deep Learning
Stereo Matching by Deep LearningStereo Matching by Deep Learning
Stereo Matching by Deep Learning
 

Similar to Image Aesthetic Assessment With Deep Learning

Gen Z - Circular Economy.pptx
Gen Z - Circular Economy.pptxGen Z - Circular Economy.pptx
Gen Z - Circular Economy.pptx
geekhouse.io
 
Multi-focus Application Presentation in ICSSE2017
Multi-focus Application Presentation in ICSSE2017Multi-focus Application Presentation in ICSSE2017
Multi-focus Application Presentation in ICSSE2017
Trong-An Bui
 
Automatic image mosaicing an approach based on fft
Automatic image mosaicing an approach based on fftAutomatic image mosaicing an approach based on fft
Automatic image mosaicing an approach based on fft
Shahrukh Javed
 
Rosa Cano_openexpo2018_sin_texto
Rosa Cano_openexpo2018_sin_textoRosa Cano_openexpo2018_sin_texto
Rosa Cano_openexpo2018_sin_texto
Rosa Cano
 
Bringing Cable TV to VR
Bringing Cable TV to VRBringing Cable TV to VR
Bringing Cable TV to VR
Arpit Mathur
 
Construir productos y transformación digital mezclando tecnología y educación...
Construir productos y transformación digital mezclando tecnología y educación...Construir productos y transformación digital mezclando tecnología y educación...
Construir productos y transformación digital mezclando tecnología y educación...
Rosa Cano
 
Atlanta Airport
Atlanta AirportAtlanta Airport
Atlanta Airport
Camille Kratlian
 
Improvement of strip thickness control through the process of data analytics
Improvement of strip thickness control through the process of data analyticsImprovement of strip thickness control through the process of data analytics
Improvement of strip thickness control through the process of data analytics
Sri Raghavan
 
Pintrace: Distributed tracing @Pinterest
Pintrace: Distributed tracing @PinterestPintrace: Distributed tracing @Pinterest
Pintrace: Distributed tracing @Pinterest
Suman Karumuri
 
Pintrace: Distributed tracing@Pinterest
Pintrace: Distributed tracing@PinterestPintrace: Distributed tracing@Pinterest
Pintrace: Distributed tracing@Pinterest
Suman Karumuri
 
Drones - What's next?
Drones - What's next?Drones - What's next?
Drones - What's next?
Speck&Tech
 
Drones: What’s Next?
Drones: What’s Next?Drones: What’s Next?
Drones: What’s Next?
Michele Dallachiesa
 
Lecture by Prof. Kelly Caylor
Lecture by Prof. Kelly CaylorLecture by Prof. Kelly Caylor
Lecture by Prof. Kelly Caylor
Salvatore Manfreda
 
cofaso Presentation
cofaso Presentationcofaso Presentation
cofaso Presentation
AndreassMuller
 
08.06.15 training occupant_engagement
08.06.15 training occupant_engagement08.06.15 training occupant_engagement
08.06.15 training occupant_engagement
melanie_bissonnette
 
Hypothesis Driven Development at Agile Australia 2015
Hypothesis Driven Development at Agile Australia 2015Hypothesis Driven Development at Agile Australia 2015
Hypothesis Driven Development at Agile Australia 2015
Georg Friedrich
 
Bluesky - Esri UK Annual Conference 2016
Bluesky - Esri UK Annual Conference 2016Bluesky - Esri UK Annual Conference 2016
Bluesky - Esri UK Annual Conference 2016
Esri UK
 
Studio Art Direct
Studio Art DirectStudio Art Direct
Studio Art Direct
Studio Art Direct
 
Salt Lake Community College - Herriman Campus General Education Building
Salt Lake Community College - Herriman Campus General Education BuildingSalt Lake Community College - Herriman Campus General Education Building
Salt Lake Community College - Herriman Campus General Education Building
HigherEdUtah
 
JacobSpence - 2016
JacobSpence - 2016JacobSpence - 2016
JacobSpence - 2016
Jacob Spence
 

Similar to Image Aesthetic Assessment With Deep Learning (20)

Gen Z - Circular Economy.pptx
Gen Z - Circular Economy.pptxGen Z - Circular Economy.pptx
Gen Z - Circular Economy.pptx
 
Multi-focus Application Presentation in ICSSE2017
Multi-focus Application Presentation in ICSSE2017Multi-focus Application Presentation in ICSSE2017
Multi-focus Application Presentation in ICSSE2017
 
Automatic image mosaicing an approach based on fft
Automatic image mosaicing an approach based on fftAutomatic image mosaicing an approach based on fft
Automatic image mosaicing an approach based on fft
 
Rosa Cano_openexpo2018_sin_texto
Rosa Cano_openexpo2018_sin_textoRosa Cano_openexpo2018_sin_texto
Rosa Cano_openexpo2018_sin_texto
 
Bringing Cable TV to VR
Bringing Cable TV to VRBringing Cable TV to VR
Bringing Cable TV to VR
 
Construir productos y transformación digital mezclando tecnología y educación...
Construir productos y transformación digital mezclando tecnología y educación...Construir productos y transformación digital mezclando tecnología y educación...
Construir productos y transformación digital mezclando tecnología y educación...
 
Atlanta Airport
Atlanta AirportAtlanta Airport
Atlanta Airport
 
Improvement of strip thickness control through the process of data analytics
Improvement of strip thickness control through the process of data analyticsImprovement of strip thickness control through the process of data analytics
Improvement of strip thickness control through the process of data analytics
 
Pintrace: Distributed tracing @Pinterest
Pintrace: Distributed tracing @PinterestPintrace: Distributed tracing @Pinterest
Pintrace: Distributed tracing @Pinterest
 
Pintrace: Distributed tracing@Pinterest
Pintrace: Distributed tracing@PinterestPintrace: Distributed tracing@Pinterest
Pintrace: Distributed tracing@Pinterest
 
Drones - What's next?
Drones - What's next?Drones - What's next?
Drones - What's next?
 
Drones: What’s Next?
Drones: What’s Next?Drones: What’s Next?
Drones: What’s Next?
 
Lecture by Prof. Kelly Caylor
Lecture by Prof. Kelly CaylorLecture by Prof. Kelly Caylor
Lecture by Prof. Kelly Caylor
 
cofaso Presentation
cofaso Presentationcofaso Presentation
cofaso Presentation
 
08.06.15 training occupant_engagement
08.06.15 training occupant_engagement08.06.15 training occupant_engagement
08.06.15 training occupant_engagement
 
Hypothesis Driven Development at Agile Australia 2015
Hypothesis Driven Development at Agile Australia 2015Hypothesis Driven Development at Agile Australia 2015
Hypothesis Driven Development at Agile Australia 2015
 
Bluesky - Esri UK Annual Conference 2016
Bluesky - Esri UK Annual Conference 2016Bluesky - Esri UK Annual Conference 2016
Bluesky - Esri UK Annual Conference 2016
 
Studio Art Direct
Studio Art DirectStudio Art Direct
Studio Art Direct
 
Salt Lake Community College - Herriman Campus General Education Building
Salt Lake Community College - Herriman Campus General Education BuildingSalt Lake Community College - Herriman Campus General Education Building
Salt Lake Community College - Herriman Campus General Education Building
 
JacobSpence - 2016
JacobSpence - 2016JacobSpence - 2016
JacobSpence - 2016
 

Recently uploaded

spirit beverages ppt without graphics.pptx
spirit beverages ppt without graphics.pptxspirit beverages ppt without graphics.pptx
spirit beverages ppt without graphics.pptx
Madan Karki
 
2008 BUILDING CONSTRUCTION Illustrated - Ching Chapter 02 The Building.pdf
2008 BUILDING CONSTRUCTION Illustrated - Ching Chapter 02 The Building.pdf2008 BUILDING CONSTRUCTION Illustrated - Ching Chapter 02 The Building.pdf
2008 BUILDING CONSTRUCTION Illustrated - Ching Chapter 02 The Building.pdf
Yasser Mahgoub
 
Hematology Analyzer Machine - Complete Blood Count
Hematology Analyzer Machine - Complete Blood CountHematology Analyzer Machine - Complete Blood Count
Hematology Analyzer Machine - Complete Blood Count
shahdabdulbaset
 
132/33KV substation case study Presentation
132/33KV substation case study Presentation132/33KV substation case study Presentation
132/33KV substation case study Presentation
kandramariana6
 
john krisinger-the science and history of the alcoholic beverage.pptx
john krisinger-the science and history of the alcoholic beverage.pptxjohn krisinger-the science and history of the alcoholic beverage.pptx
john krisinger-the science and history of the alcoholic beverage.pptx
Madan Karki
 
ISPM 15 Heat Treated Wood Stamps and why your shipping must have one
ISPM 15 Heat Treated Wood Stamps and why your shipping must have oneISPM 15 Heat Treated Wood Stamps and why your shipping must have one
ISPM 15 Heat Treated Wood Stamps and why your shipping must have one
Las Vegas Warehouse
 
Properties Railway Sleepers and Test.pptx
Properties Railway Sleepers and Test.pptxProperties Railway Sleepers and Test.pptx
Properties Railway Sleepers and Test.pptx
MDSABBIROJJAMANPAYEL
 
Redefining brain tumor segmentation: a cutting-edge convolutional neural netw...
Redefining brain tumor segmentation: a cutting-edge convolutional neural netw...Redefining brain tumor segmentation: a cutting-edge convolutional neural netw...
Redefining brain tumor segmentation: a cutting-edge convolutional neural netw...
IJECEIAES
 
Introduction to AI Safety (public presentation).pptx
Introduction to AI Safety (public presentation).pptxIntroduction to AI Safety (public presentation).pptx
Introduction to AI Safety (public presentation).pptx
MiscAnnoy1
 
KuberTENes Birthday Bash Guadalajara - K8sGPT first impressions
KuberTENes Birthday Bash Guadalajara - K8sGPT first impressionsKuberTENes Birthday Bash Guadalajara - K8sGPT first impressions
KuberTENes Birthday Bash Guadalajara - K8sGPT first impressions
Victor Morales
 
一比一原版(CalArts毕业证)加利福尼亚艺术学院毕业证如何办理
一比一原版(CalArts毕业证)加利福尼亚艺术学院毕业证如何办理一比一原版(CalArts毕业证)加利福尼亚艺术学院毕业证如何办理
一比一原版(CalArts毕业证)加利福尼亚艺术学院毕业证如何办理
ecqow
 
Data Driven Maintenance | UReason Webinar
Data Driven Maintenance | UReason WebinarData Driven Maintenance | UReason Webinar
Data Driven Maintenance | UReason Webinar
UReason
 
Generative AI leverages algorithms to create various forms of content
Generative AI leverages algorithms to create various forms of contentGenerative AI leverages algorithms to create various forms of content
Generative AI leverages algorithms to create various forms of content
Hitesh Mohapatra
 
Advanced control scheme of doubly fed induction generator for wind turbine us...
Advanced control scheme of doubly fed induction generator for wind turbine us...Advanced control scheme of doubly fed induction generator for wind turbine us...
Advanced control scheme of doubly fed induction generator for wind turbine us...
IJECEIAES
 
International Conference on NLP, Artificial Intelligence, Machine Learning an...
International Conference on NLP, Artificial Intelligence, Machine Learning an...International Conference on NLP, Artificial Intelligence, Machine Learning an...
International Conference on NLP, Artificial Intelligence, Machine Learning an...
gerogepatton
 
Mechanical Engineering on AAI Summer Training Report-003.pdf
Mechanical Engineering on AAI Summer Training Report-003.pdfMechanical Engineering on AAI Summer Training Report-003.pdf
Mechanical Engineering on AAI Summer Training Report-003.pdf
21UME003TUSHARDEB
 
Comparative analysis between traditional aquaponics and reconstructed aquapon...
Comparative analysis between traditional aquaponics and reconstructed aquapon...Comparative analysis between traditional aquaponics and reconstructed aquapon...
Comparative analysis between traditional aquaponics and reconstructed aquapon...
bijceesjournal
 
cnn.pptx Convolutional neural network used for image classication
cnn.pptx Convolutional neural network used for image classicationcnn.pptx Convolutional neural network used for image classication
cnn.pptx Convolutional neural network used for image classication
SakkaravarthiShanmug
 
IEEE Aerospace and Electronic Systems Society as a Graduate Student Member
IEEE Aerospace and Electronic Systems Society as a Graduate Student MemberIEEE Aerospace and Electronic Systems Society as a Graduate Student Member
IEEE Aerospace and Electronic Systems Society as a Graduate Student Member
VICTOR MAESTRE RAMIREZ
 
The Python for beginners. This is an advance computer language.
The Python for beginners. This is an advance computer language.The Python for beginners. This is an advance computer language.
The Python for beginners. This is an advance computer language.
sachin chaurasia
 

Recently uploaded (20)

spirit beverages ppt without graphics.pptx
spirit beverages ppt without graphics.pptxspirit beverages ppt without graphics.pptx
spirit beverages ppt without graphics.pptx
 
2008 BUILDING CONSTRUCTION Illustrated - Ching Chapter 02 The Building.pdf
2008 BUILDING CONSTRUCTION Illustrated - Ching Chapter 02 The Building.pdf2008 BUILDING CONSTRUCTION Illustrated - Ching Chapter 02 The Building.pdf
2008 BUILDING CONSTRUCTION Illustrated - Ching Chapter 02 The Building.pdf
 
Hematology Analyzer Machine - Complete Blood Count
Hematology Analyzer Machine - Complete Blood CountHematology Analyzer Machine - Complete Blood Count
Hematology Analyzer Machine - Complete Blood Count
 
132/33KV substation case study Presentation
132/33KV substation case study Presentation132/33KV substation case study Presentation
132/33KV substation case study Presentation
 
john krisinger-the science and history of the alcoholic beverage.pptx
john krisinger-the science and history of the alcoholic beverage.pptxjohn krisinger-the science and history of the alcoholic beverage.pptx
john krisinger-the science and history of the alcoholic beverage.pptx
 
ISPM 15 Heat Treated Wood Stamps and why your shipping must have one
ISPM 15 Heat Treated Wood Stamps and why your shipping must have oneISPM 15 Heat Treated Wood Stamps and why your shipping must have one
ISPM 15 Heat Treated Wood Stamps and why your shipping must have one
 
Properties Railway Sleepers and Test.pptx
Properties Railway Sleepers and Test.pptxProperties Railway Sleepers and Test.pptx
Properties Railway Sleepers and Test.pptx
 
Redefining brain tumor segmentation: a cutting-edge convolutional neural netw...
Redefining brain tumor segmentation: a cutting-edge convolutional neural netw...Redefining brain tumor segmentation: a cutting-edge convolutional neural netw...
Redefining brain tumor segmentation: a cutting-edge convolutional neural netw...
 
Introduction to AI Safety (public presentation).pptx
Introduction to AI Safety (public presentation).pptxIntroduction to AI Safety (public presentation).pptx
Introduction to AI Safety (public presentation).pptx
 
KuberTENes Birthday Bash Guadalajara - K8sGPT first impressions
KuberTENes Birthday Bash Guadalajara - K8sGPT first impressionsKuberTENes Birthday Bash Guadalajara - K8sGPT first impressions
KuberTENes Birthday Bash Guadalajara - K8sGPT first impressions
 
一比一原版(CalArts毕业证)加利福尼亚艺术学院毕业证如何办理
一比一原版(CalArts毕业证)加利福尼亚艺术学院毕业证如何办理一比一原版(CalArts毕业证)加利福尼亚艺术学院毕业证如何办理
一比一原版(CalArts毕业证)加利福尼亚艺术学院毕业证如何办理
 
Data Driven Maintenance | UReason Webinar
Data Driven Maintenance | UReason WebinarData Driven Maintenance | UReason Webinar
Data Driven Maintenance | UReason Webinar
 
Generative AI leverages algorithms to create various forms of content
Generative AI leverages algorithms to create various forms of contentGenerative AI leverages algorithms to create various forms of content
Generative AI leverages algorithms to create various forms of content
 
Advanced control scheme of doubly fed induction generator for wind turbine us...
Advanced control scheme of doubly fed induction generator for wind turbine us...Advanced control scheme of doubly fed induction generator for wind turbine us...
Advanced control scheme of doubly fed induction generator for wind turbine us...
 
International Conference on NLP, Artificial Intelligence, Machine Learning an...
International Conference on NLP, Artificial Intelligence, Machine Learning an...International Conference on NLP, Artificial Intelligence, Machine Learning an...
International Conference on NLP, Artificial Intelligence, Machine Learning an...
 
Mechanical Engineering on AAI Summer Training Report-003.pdf
Mechanical Engineering on AAI Summer Training Report-003.pdfMechanical Engineering on AAI Summer Training Report-003.pdf
Mechanical Engineering on AAI Summer Training Report-003.pdf
 
Comparative analysis between traditional aquaponics and reconstructed aquapon...
Comparative analysis between traditional aquaponics and reconstructed aquapon...Comparative analysis between traditional aquaponics and reconstructed aquapon...
Comparative analysis between traditional aquaponics and reconstructed aquapon...
 
cnn.pptx Convolutional neural network used for image classication
cnn.pptx Convolutional neural network used for image classicationcnn.pptx Convolutional neural network used for image classication
cnn.pptx Convolutional neural network used for image classication
 
IEEE Aerospace and Electronic Systems Society as a Graduate Student Member
IEEE Aerospace and Electronic Systems Society as a Graduate Student MemberIEEE Aerospace and Electronic Systems Society as a Graduate Student Member
IEEE Aerospace and Electronic Systems Society as a Graduate Student Member
 
The Python for beginners. This is an advance computer language.
The Python for beginners. This is an advance computer language.The Python for beginners. This is an advance computer language.
The Python for beginners. This is an advance computer language.
 

Image Aesthetic Assessment With Deep Learning

  • 1.
  • 2. Who am I ? M a c h i n e L e a r n i n g E n g i n e e r A m i t K u s h w a h a
  • 3. Image Aesthetics W H A T D E F I N E S A N I M A G E ? ★ Image aesthetic evaluation aims to classify photos into high quality or low quality from the perspective of human. ★ Many visual features have been explored under this formulation (handcrafted features), ranging from low-level image statistics, such as edge distributions and color histograms, to high-level photographic rules, such as the rule of thirds and golden ratio
  • 4. Beautiful Capture “ B E A U T Y I S R E A L L Y I N T H E E Y E O F T H E B E H O L D E R ” ✦ While everyone has different tastes, there are universally accepted norms when it comes to beauty – things which everyone pretty much agrees are beautiful, like sunsets or sunrises over the mountains or the ocean. A S U B J E C T I V E C O N J E C T U R E
  • 5. T E C H N I Q U E S O F I M A G E C A P T U R I N G A S U B J E C T I V E C O N J E C T U R E ✦ Image aesthetics can be affected by the different usages of lighting, contrast , and image composition Beautiful Capture
  • 6. The Two Images F A C T O R S L I K E L I G H T I N G , C O N T R A S T , A N G L E D E T E R M I N E T H E A E S T H E T I C S
  • 7. Significance of Aesthetic Assessment ✦ With the ever increasing user generated content, biggest challenge is to showcase high quality images to users. ✦ Zomato measures the performance of restaurant for ad sales with click through rate (CTR) as one of the parameter. Restaurants with High Quality Display Image have greater CTR. 01 02 04 06 WRITESOMETHING
  • 8. Photo Gallery P H O T O S D O H A V E A S T O R Y
  • 9. Let’s solve Image Aesthetics with the most disruptive technology over the last five years.
  • 10. Deep Learning S T A T E O F T H E A R T I N M A N Y F I E L D S N O W
  • 11. Fixed Size Input Constraint D E E P M O D E L I N P U T L A Y E R ✦ This constraint of fixed size input in Deep Network compromises the aesthetics of original image. input images need to be transformed via cropping, scaling, or padding, which often damages image composition, reduces image resolution, or causes image distortion, thus compromising the aesthetics of the original images. Input Layer of Network
  • 12. A M A Z I N G I N T H E I R O R I G I N A L A S P E C T R A T I O Original Image
  • 13. Transformed Image R E S I Z I N G L O S E S T H E O R I G I N A L A E S T H E T I C S O F I M A G E O R I G I N A L R E S I Z E D
  • 14. Transformed Image O R I G I N A L R E S I Z E D R E S I Z I N G L O S E S T H E O R I G I N A L A E S T H E T I C S O F I M A G E
  • 15. DEEP LEARNING Demystifying the Network ✦ The first few layers of networks are either convolution or pooling layer, followed by fully connected layers. ✦ The fixed length input is only the constraint of fully-connected layer. Be it convolution or pooling, both perform operations on input, with the spatial information.
  • 16. Spatial Pyramid Pooling ✦ Network with another pooling strategy, ‘spatial pyramid pooling’ just before the fully connected layer, makes it capable of taking input of any size and generate fixed length representation.
  • 17. Max Pooling O U T P U T I S P R O P O R T I O N A L T O I N P U T Kernel size is fixed
  • 18. Spatial Pyramid Pooling Output dimension (Bin Size , Bin Size)
  • 20. Fixed Bin Numbers Fixed Kernel Size SPP-Net CNN
  • 21. Training a SPP-net Z O M A T O D A T A S E T U S E D T R A I N I N G L O S S T R A I N I N G A C C U R A C Y M A X - A C C U R A C Y - 7 7 . 2
  • 24. It’s often neglected, but plays a major role in classification learning. S C A L E I N V A R I A N T L E A R N I N G Allows to explore CNN without the constraint of fixed size representation of input. F I X E D S I Z E I N P U T Take Aways S P A T I A L P Y R A M I D P O O L I N G N E T
  • 25. R E F E R E N C E S ✦ Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun, “Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition” ✦ Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton, ImageNet Classification with Deep Convolutional Neural Networks 2012 Composition-Preserving Deep Photo Aesthetics Assessment ✦ Long Mai, Hailin Jin, Feing Liu, Composition-Preserving Deep Photo Aesthetics Assessment
  • 26. h t t p s : / / w w w . g i t h u b . c o m / y a r d s t i c k 1 7 / h t t p s : / / w w w . l i n k e d i n . c o m / i n / y a r d s t i c k 1 7 / a m i t _ k u s h w a h a @ o u t l o o k . c o m Thank You F i n d m e h e r e

Editor's Notes

  1. To change the image behind the Mock up. Select the layer - > Right Click -> Send to Back -> Delete the image -> Drag & Drop your Own Picture -> Send to Back (again)
  2. To change the image behind the Mock up. Select the layer - > Right Click -> Send to Back -> Delete the image -> Drag & Drop your Own Picture -> Send to Back (again)
  3. To change the image behind the Mock up. Select the layer - > Right Click -> Send to Back -> Delete the image -> Drag & Drop your Own Picture -> Send to Back (again)
  4. To change the image behind the Mock up. Select the layer - > Right Click -> Send to Back -> Delete the image -> Drag & Drop your Own Picture -> Send to Back (again)