A key issue in image processing and computer vision is texture classification, which has a variety of applications such as content-based image retrieval, object recognition, scene understanding, and biomedical image analysis. The two main parts of texture classification are feature extraction and classification. Since the feature extraction plays a relatively more important role than classifiers, researchers have done lots of work on building robust and compact texture features or descriptors. Robustness and compactness are two conflicting goals, and a good texture descriptor should have a proper balance between them. Since texture images are commonly captured under different photometric and geometric transformations, robustness needs to consider gray-scale-, rotation-, and scale-invariances. In contrast, compactness means the descriptor should be low dimensional. Therefore, we research on designing robust and efficient local descriptors such as our proposed completed local derivative pattern (CLDP) (ICIP 2016) and scale-selective extended local binary pattern (SSELBP) (ICASSP 2017).
- Y. Hu, Z. Long, G. AlRegib, “Scale Selective Extended Local Binary Pattern for Texture Classification,” IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP2017), New Orleans, March 2017. [PDF] [Poster/Lec] [Bib] [Code]
- Y. Hu, Z. Long, G. AlRegib, “Completed Local Derivative Pattern for Rotation Invariant Texture Classification,” IEEE International Conference on Image Processing (ICIP), Phoenix, USA, Sept. 25-28, 2016. [PDF] [Poster/Lec] [Bib] [Code]