Name
Abstract | ||
|---|---|---|
Designing effective features is a fundamental problem in computer vision. However, it is usually difficult to achieve a great tradeoff between discriminative power and robustness. Previous works shown that spatial co-occurrence can boost the discriminative power of features. However the current existing co-occurrence features are taking few considerations to the robustness and hence suffering from sensitivity to geometric and photometric variations. In this work, we study the Transform Invariance (TI) of co-occurrence features. Concretely we formally introduce a Pairwise Transform Invariance (PTI) principle, and then propose a novel Pairwise Rotation Invariant Co-occurrence Local Binary Pattern (PRICoLBP) feature, and further extend it to incorporate multi-scale, multi-orientation, and multi-channel information. Different from other LBP variants, PRICoLBP can not only capture the spatial context co-occurrence information effectively, but also possess rotation invariance. We evaluate PRICoLBP comprehensively on nine benchmark data sets from five different perspectives, e.g., encoding strategy, rotation invariance, the number of templates, speed, and discriminative power compared to other LBP variants. Furthermore we apply PRICoLBP to six different but related applications-texture, material, flower, leaf, food, and scene classification, and demonstrate that PRICoLBP is efficient, effective, and of a well-balanced tradeoff between the discriminative power and robustness. |
Year | DOI | Venue |
|---|---|---|
2012 | 10.1109/TPAMI.2014.2316826 | IEEE Transactions on Pattern Analysis and Machine Intelligence |
Keywords | DocType | Volume |
flickr material dataset,material recognition,relative angle,local binary pattern,texture classification,pricolbp feature,pairwise transform invariance principle,rotation invariance,flower recognition,co-occurrence lbps,spatial co-occurrence,rotation invariant,rotation invariant local feature,feature extraction,pti principle,pairwise rotation invariant co-occurrence,computer vision,scene recognition,food recognition,transforms,kth-tips texture dataset,flower dataset,orientation co-occurrence,pairwise rotation invariant co-occurrence local binary pattern,leaf recognition | Conference | 36 |
Issue | ISSN | Citations |
11 | 0162-8828 | 40 |
PageRank | References | Authors |
1.01 | 43 | 6 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Xianbiao Qi | 1 | 103 | 8.25 |
| Rong Xiao | 2 | 559 | 36.27 |
| Chun-Guang Li | 3 | 310 | 17.35 |
| Yu Qiao | 4 | 2267 | 152.01 |
| Jun Guo | 5 | 1579 | 137.24 |
| Xiaoou Tang | 6 | 15728 | 670.19 |