A neighbourhood feature-based local binary pattern for texture classification

The CNN framework has gained widespread attention in texture feature analysis; however, handcrafted features still remain advantageous if computational cost needs to take precedence and in cases where textures are easily extracted with few intra-class variation. Among the handcrafted features, the local binary pattern (LBP) is extensively applied for analysing texture due to its robustness and low computational complexity. However, in local difference vector, it only utilizes the sign component, resulting in unsatisfactory classification capability. To improve classification performance, most LBP variants employ multi-feature fusion. Nevertheless, this can lead to redundant and low-discriminative sub-features and high computational complexity. To address these issues, we propose the neighbourhood feature-based local binary pattern (NF-LBP). Inspired by gradient's definition, we extract the neighbourhood feature in a local region by simply using the first-order difference and 2-norm. Next, we introduce the neighbourhood feature (NF) pattern to describe intensity changes in the neighbourhood. Finally, we combine the NF pattern with the local sign component and the centre pixel component to create the NF-LBP descriptor. This approach provides better complementary texture information to traditional local sign pattern and is less sensitive to noise. Additionally, we use an adaptive local threshold in the encoding scheme. Our experimental results of classification accuracy and F1 score on five texture databases demonstrate that our proposed NF-LBP method attains outstanding texture classification performance, outperforming existing state-of-the-art approaches. Furthermore, extensive experimental results reveal that NF-LBP is strongly robust to Gaussian noise and salt-and-pepper noise.