LPQ++: A discriminative blur-insensitive textural descriptor with spatial-channel interaction

Effective texture categorization plays an important role in effective visual recognition. Despite noticeable progress in this area, blurred-texture recognition remains a challenge. As a key reason for this, existing well-established visual descriptors (e.g., local binary patterns and deep convolutional feature) generally cannot ensure an insensitivity to blur, exhibiting a considerable decrease in performance under clear to blurring conditions. To alleviate this, we propose a discriminative blur-insensitive textural descriptor, referred to as local phase quantization plus plus (LPQ++). The main idea is to establish spatial-channel interactions between the normalized blur-insensitive feature maps yielded by a short-term Fourier transform (STFT) to enhance the descriptive power while maintaining the insensitivity to blur. In particular, spatial interactions executed within the specific STFT feature map capture the spatial correlations between neighboring points. Meanwhile, the column-wise channel interactions among the STFT feature maps help differentiate the edge and flat areas in the images; this is crucial for effective texture characterization under blurring conditions. To enable blurred texture description under dense sampling conditions, LPQ++ is extracted by calculating the spatial-channel gradient orientation histogram and embedding it into the Fisher vector. Experiments conducted on three difficult texture datasets demonstrate the effectiveness of LPQ++ for blurred-texture categorization. Our code is open-source and available at https://github.com/hustzhzhu/LPQplusplus.