Learning to Locate Informative Features for Visual Identification

Object identification (OID) is specialized recognition where the category is known (e.g. cars) and the algorithm recognizes an object's exact identity (e.g. Bob's BMW). Two special challenges characterize OID. (1) Inter-class variation is often small (many cars look alike) and may be dwarfed by illumination or pose changes. (2) There may be many classes but few or just one positive "training" examples per class. Due to (1), a solution must locate possibly subtle objectspecific salient features (a door handle) while avoiding distracting ones (a specular highlight). However, (2) rules out direct techniques of feature selection. We describe an on-line algorithm that takes one model image from a known category and builds an efficient "same" vs. "different" classification cascade by predicting the most discriminative feature set for that object. Our method not only estimates the saliency and scoring function for each candidate feature, but also model...

• Type: Journal
• Year: 2008
• Where: IJCV
• Authors: Andras Ferencz, Erik G. Learned-Miller, Jitendra Malik
• Keywords: Cars, IJCV 2008, Model Image, Object Identification