Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
10359493 | Image and Vision Computing | 2012 | 12 Pages |
Abstract
⺠We define the Maximal Translation-Tolerable Region (MTTR) to measure classifiers' sensitivity to translation-variance. ⺠We train a cascaded classifier that the MTTRs of the earlier strong classifiers in it are large and vice versa. ⺠We propose a Granularity-Adaptively-Tunable (GAT) search according to the strong classifiers' MTTRs. ⺠The recall rate is probably approximately admissible in the GAT search.
Keywords
Related Topics
Physical Sciences and Engineering
Computer Science
Computer Vision and Pattern Recognition
Authors
Wei Zheng, Luhong Liang, Hong Chang, Cher-Keng Heng, Shiguang Shan, Xilin Chen,