SlideShare a Scribd company logo
Object Class Detection
Christoph Einsiedler
Motivation
Face recognition StreetView street address recognition
http://googleonlinesecurity.blogspot.de/2014/04/street-view-and-recaptcha-technology.html
Motivation
Electronic driving aids (traffic sign recognition)
Image organisation/search (automatic tagging)
http://rossel-vw.de/p_50679/de/models/cc/galerie.html
Problem description
Object Class Detection
Classification
Localization
Face recognition etc.
as special cases
http://pascallin.ecs.soton.ac.uk/challenges/VOC/voc2012/
Problem description
robustness
Big differences between
instances of the same
category
Small differences between
instances of different
categories
complexity
Huge number of categories
Algorithms
Find interest points
SIFT
…
Interest point description
SIFT
HOG
…
Image description
Bag-of-features
…
Algorithms
SIFT
1. Scale-space extrema detection
Convolution with Gaussian filters at different scales
Calculation of differences
Points with maximal differences as keypoints
http://www.cs.ubc.ca/~lowe/papers/ijcv04.pdf
Algorithms
SIFT
2. Keypoint localization
Calculation of interpolatated positions
Removal of keypoints with low contrast
Removal of poorly located keypoints on edges
Algorithms
SIFT
3. Orientation assignment
Gradients of Gaussian smoothed image are considered (scale invariance)
Magnitudes and directions are put into a histogram
Orientation of the highest peak is assigned (rotation invariance)
Algorithms
SIFT
4. Keypoint descriptor
(illumination, viewing angle,… invariance)
Algorithms
Find interest points
SIFT •
…
Interest point description
SIFT •
HOG
…
Picture description
Bag-of-features
…
Algorithms
HOG
1. Gamma/Color normalization
Greyscale, RGB or LAB tested
Not neccessary
http://lear.inrialpes.fr/people/triggs/pubs/Dalal-cvpr05.pdf
Algorithms
HOG
2. Gradient computation
Different masks tested (e.g. sobel masks)
1-D centered mask best
Algorithms
HOG
3. Orientation binning
Edge orientation histogram for each cell of the image
Orientations grouped into 9 bins (0-180°)
Algorithms
HOG
4. Normalization and descriptor blocks
Image divided into blocks (R-HOG, C-HOG)
Normalization
Aggregation into one vector
Algorithms
Find interest points
SIFT •
…
Interest point description
SIFT •
HOG •
…
Picture description
Bag-of-features
…
Algorithms
Bag-of-features
origins in document classification
later also used for object class detetcion in images
http://www.dtic.mil/dtic/tr/fulltext/u2/a307731.pdf
Algorithms
Bag-of-features
Clustering
create signatures for images
http://www.vision.caltech.edu/html-files/EE148-2005-Spring/pprs/dorko_schmid_obj_class_rec.pdf
Algorithms
Find interest points
SIFT •
…
Interest point description
SIFT •
HOG •
…
Picture description
Bag-of-features •
…
Evaluation
Comparability not easy
Pascal VOC often used
Benchmark (training data, test data)
Images from Flickr
Manually annotated
Annual competitions
Evaluation
Classification/Detection
Competitions
Classification
Localization
Segmentation Competition
Action Classification Competition
http://pascallin.ecs.soton.ac.uk/challenges/VOC/voc2012/
Evaluation
Classification/detection competition
20 classes of objects:
Class Example image 1 Example image 2
aeroplane
bicycle
http://pascallin.ecs.soton.ac.uk/challenges/VOC/voc2012/
Evaluation
Class Example image 1 Example image 2
bird
boat
bottle
http://pascallin.ecs.soton.ac.uk/challenges/VOC/voc2012/
Evaluation
Class
bus
car
cat
chair
cow
diningtable
dog
horse
Class
motorbike
person
pottet plant
sheep
sofa
diningtable
train
tv/monitor
Evaluation
Evaluation measures:
Recall
Precision
Average Precision
http://pascallin.ecs.soton.ac.uk/challenges/VOC/voc2012/
Evaluation
Pascal VOC 2012 results
algorithm mean aero
plane
bicycle bird boat bottle bus car cat chair cow dining
table
dog horse motor
bike
person pottet
plant
sheep sofa train tv/
moni-
tor
NUSPL_CTX_
GPM_SCM
82.2 97.3 84.2 80.8 85.3 60.8 89.9 86.8 89.3 75.4 77.8 75.1 83.0 87.5 90.1 95.0 57.8 79.2 73.4 94.5 80.7
NUSPSL_CTX_GPM 78.6 95.5 81.1 79.4 82.5 58.2 87.7 84.1 83.1 68.5 72.8 68.5 76.4 83.3 87.5 92.8 56.5 77.8 67.0 91.2 77.6
NLPR_PLS_SSVW 78.3 94.5 82.6 79.4 80.7 57.8 87.8 85.5 83.9 66.6 74.2 69.4 75.2 83.0 88.2 93.6 56.2 75.6 64.1 90.0 76.6
NUS_Context_SVM 78.3 95.3 81.5 78.9 81.8 57.5 87.3 83.7 82.3 68.4 75.0 68.5 75.8 82.9 86.7 92.7 56.8 77.7 66.1 90.7 77.1
Semi-Semantic
Visual Words &
Partial Least Sqares
78.3 94.5 82.6 79.4 80.7 57.8 87.8 85.5 83.9 66.6 74.2 69.4 75.2 83.0 88.2 93.6 56.2 75.6 64.1 90.0 76.6
NUSPSL_CTX_GPM_
SVM
76.7 94.3 78.5 76.4 80.0 57.0 86.3 82.1 81.5 65.6 74.7 66.5 73.4 81.9 85.4 91.9 53.2 74.0 65.1 89.5 76.1
CVC_UVA_UNITN 74.3 92.0 74.2 73.0 77.5 54.3 85.2 81.9 76.4 65.2 63.2 68.5 68.9 78.2 81.0 91.6 55.9 69.4 65.4 86.7 77.4
UvA_UNITN_
MostTellingMonkey
73.4 90.1 74.1 66.6 76.0 57.0 85.6 81.2 74.5 63.5 62.7 64.5 66.6 76.5 81.3 90.8 58.7 69.5 66.3 84.7 77.3
CVC_CLS 71.0 89.3 70.9 69.8 73.9 51.3 84.8 79.6 72.9 63.8 59.4 64.1 64.7 75.5 79.2 91.4 42.7 63.2 61.9 86.7 73.8
MSRA_USTC_HIGH_
ORDER_SVM
70.5 92.8 74.8 69.6 76.1 47.3 83.5 76.4 76.9 59.8 54.5 63.5 67.0 75.1 78.8 90.4 43.2 63.3 60.4 85.6 71.2
Thank you for your attention.

More Related Content

Similar to Seminar Medieninformatik: Object Class Detection

Using amazon machine learning to identify trends in io t data technical 201
Using amazon machine learning to identify trends in io t data   technical 201Using amazon machine learning to identify trends in io t data   technical 201
Using amazon machine learning to identify trends in io t data technical 201
Amazon Web Services
 
Using Amazon Machine Learning to Identify Trends in IoT Data - Technical 201
Using Amazon Machine Learning to Identify Trends in IoT Data - Technical 201Using Amazon Machine Learning to Identify Trends in IoT Data - Technical 201
Using Amazon Machine Learning to Identify Trends in IoT Data - Technical 201
Amazon Web Services
 
Lunchlezing landelijke keuzemodellen voor Octavius
Lunchlezing landelijke keuzemodellen voor OctaviusLunchlezing landelijke keuzemodellen voor Octavius
Lunchlezing landelijke keuzemodellen voor Octavius
Luuk Brederode
 
Machine Learning Model for M.S admissions
Machine Learning Model for M.S admissionsMachine Learning Model for M.S admissions
Machine Learning Model for M.S admissions
Omkar Rane
 
Traffic Congestion using IOT
Traffic Congestion using IOTTraffic Congestion using IOT
Traffic Congestion using IOT
SayantanGhosh58
 
When Micromobility Attacks
When Micromobility AttacksWhen Micromobility Attacks
When Micromobility Attacks
Horace Dediu
 
Aalto_Thesis_Ayman
Aalto_Thesis_AymanAalto_Thesis_Ayman
Aalto_Thesis_Ayman
Ayman Elkadi
 
Deep Learning for Developers (October 2017)
Deep Learning for Developers (October 2017)Deep Learning for Developers (October 2017)
Deep Learning for Developers (October 2017)
Julien SIMON
 
Minor Transport
Minor TransportMinor Transport
Minor Transport
James Arnold
 
Spark Summit Dublin 2017 - MemSQL - Real-Time Image Recognition
Spark Summit Dublin 2017 - MemSQL - Real-Time Image RecognitionSpark Summit Dublin 2017 - MemSQL - Real-Time Image Recognition
Spark Summit Dublin 2017 - MemSQL - Real-Time Image Recognition
SingleStore
 
VEHICLES AND TOURIST FREQUENCY TRACKING USING OPENCV
VEHICLES AND TOURIST FREQUENCY TRACKING USING OPENCVVEHICLES AND TOURIST FREQUENCY TRACKING USING OPENCV
VEHICLES AND TOURIST FREQUENCY TRACKING USING OPENCV
IRJET Journal
 
GPS en verplaatsingsgedrag
GPS en verplaatsingsgedrag GPS en verplaatsingsgedrag
GPS en verplaatsingsgedrag
Kantar TNS
 
T.O.M 3.0 (Final PRINT)
T.O.M 3.0 (Final PRINT)T.O.M 3.0 (Final PRINT)
T.O.M 3.0 (Final PRINT)
Amit Bhakta
 
dissertation_hrncir_2016_final
dissertation_hrncir_2016_finaldissertation_hrncir_2016_final
dissertation_hrncir_2016_final
Jan Hrnčíř
 
AUTOMATIC LICENSE PLATE RECOGNITION USING YOLOV4 AND TESSERACT OCR
AUTOMATIC LICENSE PLATE RECOGNITION USING YOLOV4 AND TESSERACT OCRAUTOMATIC LICENSE PLATE RECOGNITION USING YOLOV4 AND TESSERACT OCR
AUTOMATIC LICENSE PLATE RECOGNITION USING YOLOV4 AND TESSERACT OCR
Angie Miller
 
Y.Chan A.Fowe AHTD Presentation
Y.Chan A.Fowe AHTD PresentationY.Chan A.Fowe AHTD Presentation
Y.Chan A.Fowe AHTD Presentation
itsmetalab
 
Evaluating Surrogate Models for Robot Swarm Simulations
Evaluating Surrogate Models for Robot Swarm SimulationsEvaluating Surrogate Models for Robot Swarm Simulations
Evaluating Surrogate Models for Robot Swarm Simulations
Daniel H. Stolfi
 
energia
energiaenergia
From SQL to Pandas
From SQL to PandasFrom SQL to Pandas
From SQL to Pandas
Walter Gentile
 
Spec00446
Spec00446Spec00446
Spec00446
guest2f67152
 

Similar to Seminar Medieninformatik: Object Class Detection (20)

Using amazon machine learning to identify trends in io t data technical 201
Using amazon machine learning to identify trends in io t data   technical 201Using amazon machine learning to identify trends in io t data   technical 201
Using amazon machine learning to identify trends in io t data technical 201
 
Using Amazon Machine Learning to Identify Trends in IoT Data - Technical 201
Using Amazon Machine Learning to Identify Trends in IoT Data - Technical 201Using Amazon Machine Learning to Identify Trends in IoT Data - Technical 201
Using Amazon Machine Learning to Identify Trends in IoT Data - Technical 201
 
Lunchlezing landelijke keuzemodellen voor Octavius
Lunchlezing landelijke keuzemodellen voor OctaviusLunchlezing landelijke keuzemodellen voor Octavius
Lunchlezing landelijke keuzemodellen voor Octavius
 
Machine Learning Model for M.S admissions
Machine Learning Model for M.S admissionsMachine Learning Model for M.S admissions
Machine Learning Model for M.S admissions
 
Traffic Congestion using IOT
Traffic Congestion using IOTTraffic Congestion using IOT
Traffic Congestion using IOT
 
When Micromobility Attacks
When Micromobility AttacksWhen Micromobility Attacks
When Micromobility Attacks
 
Aalto_Thesis_Ayman
Aalto_Thesis_AymanAalto_Thesis_Ayman
Aalto_Thesis_Ayman
 
Deep Learning for Developers (October 2017)
Deep Learning for Developers (October 2017)Deep Learning for Developers (October 2017)
Deep Learning for Developers (October 2017)
 
Minor Transport
Minor TransportMinor Transport
Minor Transport
 
Spark Summit Dublin 2017 - MemSQL - Real-Time Image Recognition
Spark Summit Dublin 2017 - MemSQL - Real-Time Image RecognitionSpark Summit Dublin 2017 - MemSQL - Real-Time Image Recognition
Spark Summit Dublin 2017 - MemSQL - Real-Time Image Recognition
 
VEHICLES AND TOURIST FREQUENCY TRACKING USING OPENCV
VEHICLES AND TOURIST FREQUENCY TRACKING USING OPENCVVEHICLES AND TOURIST FREQUENCY TRACKING USING OPENCV
VEHICLES AND TOURIST FREQUENCY TRACKING USING OPENCV
 
GPS en verplaatsingsgedrag
GPS en verplaatsingsgedrag GPS en verplaatsingsgedrag
GPS en verplaatsingsgedrag
 
T.O.M 3.0 (Final PRINT)
T.O.M 3.0 (Final PRINT)T.O.M 3.0 (Final PRINT)
T.O.M 3.0 (Final PRINT)
 
dissertation_hrncir_2016_final
dissertation_hrncir_2016_finaldissertation_hrncir_2016_final
dissertation_hrncir_2016_final
 
AUTOMATIC LICENSE PLATE RECOGNITION USING YOLOV4 AND TESSERACT OCR
AUTOMATIC LICENSE PLATE RECOGNITION USING YOLOV4 AND TESSERACT OCRAUTOMATIC LICENSE PLATE RECOGNITION USING YOLOV4 AND TESSERACT OCR
AUTOMATIC LICENSE PLATE RECOGNITION USING YOLOV4 AND TESSERACT OCR
 
Y.Chan A.Fowe AHTD Presentation
Y.Chan A.Fowe AHTD PresentationY.Chan A.Fowe AHTD Presentation
Y.Chan A.Fowe AHTD Presentation
 
Evaluating Surrogate Models for Robot Swarm Simulations
Evaluating Surrogate Models for Robot Swarm SimulationsEvaluating Surrogate Models for Robot Swarm Simulations
Evaluating Surrogate Models for Robot Swarm Simulations
 
energia
energiaenergia
energia
 
From SQL to Pandas
From SQL to PandasFrom SQL to Pandas
From SQL to Pandas
 
Spec00446
Spec00446Spec00446
Spec00446
 

Recently uploaded

Generating privacy-protected synthetic data using Secludy and Milvus
Generating privacy-protected synthetic data using Secludy and MilvusGenerating privacy-protected synthetic data using Secludy and Milvus
Generating privacy-protected synthetic data using Secludy and Milvus
Zilliz
 
Best 20 SEO Techniques To Improve Website Visibility In SERP
Best 20 SEO Techniques To Improve Website Visibility In SERPBest 20 SEO Techniques To Improve Website Visibility In SERP
Best 20 SEO Techniques To Improve Website Visibility In SERP
Pixlogix Infotech
 
GraphRAG for Life Science to increase LLM accuracy
GraphRAG for Life Science to increase LLM accuracyGraphRAG for Life Science to increase LLM accuracy
GraphRAG for Life Science to increase LLM accuracy
Tomaz Bratanic
 
Programming Foundation Models with DSPy - Meetup Slides
Programming Foundation Models with DSPy - Meetup SlidesProgramming Foundation Models with DSPy - Meetup Slides
Programming Foundation Models with DSPy - Meetup Slides
Zilliz
 
Public CyberSecurity Awareness Presentation 2024.pptx
Public CyberSecurity Awareness Presentation 2024.pptxPublic CyberSecurity Awareness Presentation 2024.pptx
Public CyberSecurity Awareness Presentation 2024.pptx
marufrahmanstratejm
 
June Patch Tuesday
June Patch TuesdayJune Patch Tuesday
June Patch Tuesday
Ivanti
 
Monitoring and Managing Anomaly Detection on OpenShift.pdf
Monitoring and Managing Anomaly Detection on OpenShift.pdfMonitoring and Managing Anomaly Detection on OpenShift.pdf
Monitoring and Managing Anomaly Detection on OpenShift.pdf
Tosin Akinosho
 
Salesforce Integration for Bonterra Impact Management (fka Social Solutions A...
Salesforce Integration for Bonterra Impact Management (fka Social Solutions A...Salesforce Integration for Bonterra Impact Management (fka Social Solutions A...
Salesforce Integration for Bonterra Impact Management (fka Social Solutions A...
Jeffrey Haguewood
 
leewayhertz.com-AI in predictive maintenance Use cases technologies benefits ...
leewayhertz.com-AI in predictive maintenance Use cases technologies benefits ...leewayhertz.com-AI in predictive maintenance Use cases technologies benefits ...
leewayhertz.com-AI in predictive maintenance Use cases technologies benefits ...
alexjohnson7307
 
AWS Cloud Cost Optimization Presentation.pptx
AWS Cloud Cost Optimization Presentation.pptxAWS Cloud Cost Optimization Presentation.pptx
AWS Cloud Cost Optimization Presentation.pptx
HarisZaheer8
 
Introduction of Cybersecurity with OSS at Code Europe 2024
Introduction of Cybersecurity with OSS  at Code Europe 2024Introduction of Cybersecurity with OSS  at Code Europe 2024
Introduction of Cybersecurity with OSS at Code Europe 2024
Hiroshi SHIBATA
 
5th LF Energy Power Grid Model Meet-up Slides
5th LF Energy Power Grid Model Meet-up Slides5th LF Energy Power Grid Model Meet-up Slides
5th LF Energy Power Grid Model Meet-up Slides
DanBrown980551
 
Overcoming the PLG Trap: Lessons from Canva's Head of Sales & Head of EMEA Da...
Overcoming the PLG Trap: Lessons from Canva's Head of Sales & Head of EMEA Da...Overcoming the PLG Trap: Lessons from Canva's Head of Sales & Head of EMEA Da...
Overcoming the PLG Trap: Lessons from Canva's Head of Sales & Head of EMEA Da...
saastr
 
Your One-Stop Shop for Python Success: Top 10 US Python Development Providers
Your One-Stop Shop for Python Success: Top 10 US Python Development ProvidersYour One-Stop Shop for Python Success: Top 10 US Python Development Providers
Your One-Stop Shop for Python Success: Top 10 US Python Development Providers
akankshawande
 
zkStudyClub - LatticeFold: A Lattice-based Folding Scheme and its Application...
zkStudyClub - LatticeFold: A Lattice-based Folding Scheme and its Application...zkStudyClub - LatticeFold: A Lattice-based Folding Scheme and its Application...
zkStudyClub - LatticeFold: A Lattice-based Folding Scheme and its Application...
Alex Pruden
 
How to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdf
How to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdfHow to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdf
How to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdf
Chart Kalyan
 
Driving Business Innovation: Latest Generative AI Advancements & Success Story
Driving Business Innovation: Latest Generative AI Advancements & Success StoryDriving Business Innovation: Latest Generative AI Advancements & Success Story
Driving Business Innovation: Latest Generative AI Advancements & Success Story
Safe Software
 
HCL Notes and Domino License Cost Reduction in the World of DLAU
HCL Notes and Domino License Cost Reduction in the World of DLAUHCL Notes and Domino License Cost Reduction in the World of DLAU
HCL Notes and Domino License Cost Reduction in the World of DLAU
panagenda
 
TrustArc Webinar - 2024 Global Privacy Survey
TrustArc Webinar - 2024 Global Privacy SurveyTrustArc Webinar - 2024 Global Privacy Survey
TrustArc Webinar - 2024 Global Privacy Survey
TrustArc
 
Serial Arm Control in Real Time Presentation
Serial Arm Control in Real Time PresentationSerial Arm Control in Real Time Presentation
Serial Arm Control in Real Time Presentation
tolgahangng
 

Recently uploaded (20)

Generating privacy-protected synthetic data using Secludy and Milvus
Generating privacy-protected synthetic data using Secludy and MilvusGenerating privacy-protected synthetic data using Secludy and Milvus
Generating privacy-protected synthetic data using Secludy and Milvus
 
Best 20 SEO Techniques To Improve Website Visibility In SERP
Best 20 SEO Techniques To Improve Website Visibility In SERPBest 20 SEO Techniques To Improve Website Visibility In SERP
Best 20 SEO Techniques To Improve Website Visibility In SERP
 
GraphRAG for Life Science to increase LLM accuracy
GraphRAG for Life Science to increase LLM accuracyGraphRAG for Life Science to increase LLM accuracy
GraphRAG for Life Science to increase LLM accuracy
 
Programming Foundation Models with DSPy - Meetup Slides
Programming Foundation Models with DSPy - Meetup SlidesProgramming Foundation Models with DSPy - Meetup Slides
Programming Foundation Models with DSPy - Meetup Slides
 
Public CyberSecurity Awareness Presentation 2024.pptx
Public CyberSecurity Awareness Presentation 2024.pptxPublic CyberSecurity Awareness Presentation 2024.pptx
Public CyberSecurity Awareness Presentation 2024.pptx
 
June Patch Tuesday
June Patch TuesdayJune Patch Tuesday
June Patch Tuesday
 
Monitoring and Managing Anomaly Detection on OpenShift.pdf
Monitoring and Managing Anomaly Detection on OpenShift.pdfMonitoring and Managing Anomaly Detection on OpenShift.pdf
Monitoring and Managing Anomaly Detection on OpenShift.pdf
 
Salesforce Integration for Bonterra Impact Management (fka Social Solutions A...
Salesforce Integration for Bonterra Impact Management (fka Social Solutions A...Salesforce Integration for Bonterra Impact Management (fka Social Solutions A...
Salesforce Integration for Bonterra Impact Management (fka Social Solutions A...
 
leewayhertz.com-AI in predictive maintenance Use cases technologies benefits ...
leewayhertz.com-AI in predictive maintenance Use cases technologies benefits ...leewayhertz.com-AI in predictive maintenance Use cases technologies benefits ...
leewayhertz.com-AI in predictive maintenance Use cases technologies benefits ...
 
AWS Cloud Cost Optimization Presentation.pptx
AWS Cloud Cost Optimization Presentation.pptxAWS Cloud Cost Optimization Presentation.pptx
AWS Cloud Cost Optimization Presentation.pptx
 
Introduction of Cybersecurity with OSS at Code Europe 2024
Introduction of Cybersecurity with OSS  at Code Europe 2024Introduction of Cybersecurity with OSS  at Code Europe 2024
Introduction of Cybersecurity with OSS at Code Europe 2024
 
5th LF Energy Power Grid Model Meet-up Slides
5th LF Energy Power Grid Model Meet-up Slides5th LF Energy Power Grid Model Meet-up Slides
5th LF Energy Power Grid Model Meet-up Slides
 
Overcoming the PLG Trap: Lessons from Canva's Head of Sales & Head of EMEA Da...
Overcoming the PLG Trap: Lessons from Canva's Head of Sales & Head of EMEA Da...Overcoming the PLG Trap: Lessons from Canva's Head of Sales & Head of EMEA Da...
Overcoming the PLG Trap: Lessons from Canva's Head of Sales & Head of EMEA Da...
 
Your One-Stop Shop for Python Success: Top 10 US Python Development Providers
Your One-Stop Shop for Python Success: Top 10 US Python Development ProvidersYour One-Stop Shop for Python Success: Top 10 US Python Development Providers
Your One-Stop Shop for Python Success: Top 10 US Python Development Providers
 
zkStudyClub - LatticeFold: A Lattice-based Folding Scheme and its Application...
zkStudyClub - LatticeFold: A Lattice-based Folding Scheme and its Application...zkStudyClub - LatticeFold: A Lattice-based Folding Scheme and its Application...
zkStudyClub - LatticeFold: A Lattice-based Folding Scheme and its Application...
 
How to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdf
How to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdfHow to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdf
How to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdf
 
Driving Business Innovation: Latest Generative AI Advancements & Success Story
Driving Business Innovation: Latest Generative AI Advancements & Success StoryDriving Business Innovation: Latest Generative AI Advancements & Success Story
Driving Business Innovation: Latest Generative AI Advancements & Success Story
 
HCL Notes and Domino License Cost Reduction in the World of DLAU
HCL Notes and Domino License Cost Reduction in the World of DLAUHCL Notes and Domino License Cost Reduction in the World of DLAU
HCL Notes and Domino License Cost Reduction in the World of DLAU
 
TrustArc Webinar - 2024 Global Privacy Survey
TrustArc Webinar - 2024 Global Privacy SurveyTrustArc Webinar - 2024 Global Privacy Survey
TrustArc Webinar - 2024 Global Privacy Survey
 
Serial Arm Control in Real Time Presentation
Serial Arm Control in Real Time PresentationSerial Arm Control in Real Time Presentation
Serial Arm Control in Real Time Presentation
 

Seminar Medieninformatik: Object Class Detection

Editor's Notes

  1. Automatische Medienanalyse und offene Daten
  2. Thema des Seminars: Automatische Medienanalyse -> Bilder
  3. Thema des Seminars: Automatische Medienanalyse -> Bilder
  4. Umwelt verändert sich
  5. Scale-invariant feature transform
  6. Location: Taylor Expansion der Gauß-Differenz
  7. Histogramm: 36 bins/Klassen => jeweils 10 Grad
  8. Normalerweise 16x16 -> 4x4 statt wie hier 8x8 -> 2x2 4 x 4 = 16 histograms each with 8 bins the vector has 128 -> hohe Dimension
  9. Histogram of oriented gradients
  10. 1-D Kernel Filter wie [−1,0,1]; besser als Sobel Masken
  11. R-HOG: rectangular C-Hog: circular
  12. https://www.cs.cmu.edu/~efros/courses/AP06/Papers/csurka-eccv-04.pdf
  13. K-means: http://www.labri.fr/perso/bpinaud/userfiles/downloads/hartigan_1979_kmeans.pdf
  14. Automatische Medienanalyse und offene Daten