Building a classification cascade for visual identification from one example

@inproceedings{citeulike:1203830, abstract = {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) Interclass 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 object-specific salient features (a door handle) while avoiding distracting ones (a specular highlight). However, (2) rules out direct techniques of feature selection. We describe an online 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 models the dependency between features, building an ordered feature sequence unique to a specific model image, maximizing cumulative information content. Learned stopping thresholds make the classifier very efficient. To make this possible, category-specific characteristics are learned automatically in an off-line training procedure from labeled image pairs of the category, without prior knowledge about the category. Our method, using the same algorithm for both cars and faces, outperforms a wide variety of other methods.}, author = {Ferencz, A. and Learned-Miller, E. G. and Malik, J. }, citeulike-article-id = {1203830}, journal = {Computer Vision, 2005. ICCV 2005. Tenth IEEE International Conference on}, keywords = {bag-of-features, object-categorization, object-identification, object-recognition, photo2search, reading, recognition, spatial-relationship, statistical-model}, pages = {286--293 Vol. 1}, posted-at = {2007-04-03 09:13:12}, priority = {2}, title = {Building a classification cascade for visual identification from one example}, url = {http://ieeexplore.ieee.org/xpls/abs\_all.jsp?arnumber=1541269}, volume = {1}, year = {2005} }

TY - CONF ID - citeulike:1203830 L3 - citeulike-article-id:1203830 N2 - 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) Interclass 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 object-specific salient features (a door handle) while avoiding distracting ones (a specular highlight). However, (2) rules out direct techniques of feature selection. We describe an online 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 models the dependency between features, building an ordered feature sequence unique to a specific model image, maximizing cumulative information content. Learned stopping thresholds make the classifier very efficient. To make this possible, category-specific characteristics are learned automatically in an off-line training procedure from labeled image pairs of the category, without prior knowledge about the category. Our method, using the same algorithm for both cars and faces, outperforms a wide variety of other methods. JF - Computer Vision, 2005. ICCV 2005. Tenth IEEE International Conference on EP - 293 Vol. 1 TI - Building a classification cascade for visual identification from one example VL - 1 SP - 286 KW - bag-of-features KW - object-categorization KW - object-identification KW - object-recognition KW - photo2search KW - reading KW - recognition KW - spatial-relationship KW - statistical-model AU - Ferencz, A AU - Learned-Miller, EG AU - Malik, J PY - 2005/// UR - http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1541269 ER -