Deep Local Binary Patterns
This work addresses a domain-specific problem in texture analysis and computer vision by enhancing LBP expressiveness, though it appears incremental as it builds on existing LBP methods with deep learning ideas.
The paper tackled the limitation of Local Binary Patterns (LBP) in capturing high-level image features by proposing Deep LBP, which applies LBP operators with increasing abstraction levels, resulting in improved performance over traditional and multiscale LBP across multiple datasets.
Local Binary Pattern (LBP) is a traditional descriptor for texture analysis that gained attention in the last decade. Being robust to several properties such as invariance to illumination translation and scaling, LBPs achieved state-of-the-art results in several applications. However, LBPs are not able to capture high-level features from the image, merely encoding features with low abstraction levels. In this work, we propose Deep LBP, which borrow ideas from the deep learning community to improve LBP expressiveness. By using parametrized data-driven LBP, we enable successive applications of the LBP operators with increasing abstraction levels. We validate the relevance of the proposed idea in several datasets from a wide range of applications. Deep LBP improved the performance of traditional and multiscale LBP in all cases.