Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.
Image Recognitionin Digital Merchandising Industry
What is Merchandising?
Digital Merchandising Benefits• Improved Service Level Monitoring• Reduced Data Collection Time• Out of Stock Reduction• I...
What is Computer Vision?“Computer vision is a field that includesmethods for acquiring, processing,analyzing, and understa...
Computer Vision EvolutionComputerVisionArtificialIntelligenceImageProcessingPatternRecognitionRoboticsMachine Vision1960s1...
Recognition Steps
Image acquisition
Image preprocessing
Feature extraction
Descriptor extraction
Descriptor matching
Filtering
Object Identification
Demo
Algorithms and Libraries
Computer Vision Algorithms• SURF• SIFT• FAST• FREAK• ORB• RANSAC
Computer Vision Libraries• OpenCV• EmguCV• FastCV• JavaCV
Results
01020304050607080900.3 0.6 0.7 0.8 0.9 1 1.2 2 3 5 8RecognitionqualityImage sizeRecognition quality depending on image size
?
Image Recognition in Digital Merchandising Industry
Image Recognition in Digital Merchandising Industry
Image Recognition in Digital Merchandising Industry
Image Recognition in Digital Merchandising Industry
Upcoming SlideShare
Loading in …5
×

Image Recognition in Digital Merchandising Industry

1,531 views

Published on

by Vitalii Yuryev

Published in: Technology, Business
  • Be the first to comment

Image Recognition in Digital Merchandising Industry

  1. 1. Image Recognitionin Digital Merchandising Industry
  2. 2. What is Merchandising?
  3. 3. Digital Merchandising Benefits• Improved Service Level Monitoring• Reduced Data Collection Time• Out of Stock Reduction• Increase in SKU Availability• Merchandiser Self-discipline
  4. 4. What is Computer Vision?“Computer vision is a field that includesmethods for acquiring, processing,analyzing, and understanding images inorder to produce numerical or symbolicinformation”Wikipedia
  5. 5. Computer Vision EvolutionComputerVisionArtificialIntelligenceImageProcessingPatternRecognitionRoboticsMachine Vision1960s1970sEdgedetectionLine Labeling1980s1990s Face trackingFacerecognition2000sFeature-basedrecognitionImage-basedmodelingImage-basedrenderingRegion-basedrecognitionHigh dynamicrangeEmotionrecognitionRoboticVisionNeural networkbased recognition2010sPhysicsFirst digitalcameraMegapixelsensorCMOS chipSURFSIFTORBBRIEFFREAKHOG GLOHHaar-cascadesViola-JonesFASTLatent SVMDeep NNLSTM NNMD LSTM NNRPROPFR NNBoW
  6. 6. Recognition Steps
  7. 7. Image acquisition
  8. 8. Image preprocessing
  9. 9. Feature extraction
  10. 10. Descriptor extraction
  11. 11. Descriptor matching
  12. 12. Filtering
  13. 13. Object Identification
  14. 14. Demo
  15. 15. Algorithms and Libraries
  16. 16. Computer Vision Algorithms• SURF• SIFT• FAST• FREAK• ORB• RANSAC
  17. 17. Computer Vision Libraries• OpenCV• EmguCV• FastCV• JavaCV
  18. 18. Results
  19. 19. 01020304050607080900.3 0.6 0.7 0.8 0.9 1 1.2 2 3 5 8RecognitionqualityImage sizeRecognition quality depending on image size
  20. 20. ?

×