Abstract | ||
---|---|---|
Local binary pattern (LBP) and its variants have been used in scene recognition. However, most existing approaches rely on a pre-defined LBP structure to extract features. Those pre-defined structures can be generalized as the patterns constructed from the binarized pixel differences in a local neighborhood. Instead of using a handcraft structure, we propose to learn binarized pixel-difference patterns (BPP). We cast the problem as a feature selection problem and solve it by an incremental search via the criterion of minimum-redundancymaximum- relevance. Then, BPP features are extracted based on the structures derived. On two challenging scene recognition databases, the proposed approach significantly outperforms the state of the arts. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1109/ICIP.2013.6738514 | 2013 20TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP 2013) |
Keywords | Field | DocType |
Local Binary Pattern, Feature Selection, Binarized Pixel-difference Pattern, Scene Recognition | Computer vision,Feature selection,Pattern recognition,Feature (computer vision),Computer science,Local binary patterns,Incremental search,Feature extraction,Feature (machine learning),Pixel,Artificial intelligence,Image resolution | Conference |
ISSN | Citations | PageRank |
1522-4880 | 8 | 0.45 |
References | Authors | |
13 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jianfeng Ren | 1 | 291 | 16.97 |
Xudong Jiang | 2 | 1885 | 117.85 |
Junsong Yuan | 3 | 3703 | 187.68 |