Learning Visual Similarity Measures for Comparing Never Seen Objects By: Eric Nowark, Frederic Juric Presented by: Khoa Tran
Outline 1.) Purpose 2.) Methodology 3.) Results
Purpose Object Recognition Train Images Test Images
Methodology Preview A.) Corresponding patch pair B.) Quantizing patch pair C.) Patch pair similarity measure
Object Recognition 1.) Images 2.) Feature Extraction 3.) Model Database 4.) Matching a.) Hypothesis Generation b.) Hypothesis Verification Images Features Extraction Model Database Hypothesis Generation Hypothesis Verification Matching
Images Total: images, - 21 different objects Training Data Set positive image pairs negative image pairs - 14 different objects Testing Data Set positive image pairs negative image pairs - 7 different objects
Feature Extraction Patches Normalized Cross Correlation SIFT Descriptors Matrix representation
Model Database Extremely Randomized Binary Decision Tree SIFT Descriptors Geometric Information Information Gain
Model Database – SIFT Descriptors
Model Database
Hypothesis Generation – Similar Measure Similar Measure Support Vector Machine
Hypothesis Generation Ferencz and MalikFaces in the NewsDataset
C.) Hypothesis Verification Sammon mapping for toy cars
Results 1.) Toy Cars2.) Ferencz 3.) Faces4.) Coil 100
Reference Eric Nowak and Fredric Jurie; "Learning Visual Similarity Measures for Comparing Never Seen Objects” ;Computer Vision and Pattern Recognition 2007 (CVPR'07);