LPQ++: A discriminative blur-insensitive textural descriptor with spatial-channel interaction
Autor: | Zhu Zihao, Zhiwen Fang, Li Shuai, Joey Tianyi Zhou, Zhiguo Cao, Yang Xiao |
---|---|
Rok vydání: | 2021 |
Předmět: |
Normalization (statistics)
Information Systems and Management Channel (digital image) Computer science Local binary patterns ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION 02 engineering and technology Texture (geology) Theoretical Computer Science Discriminative model Artificial Intelligence Histogram 0202 electrical engineering electronic engineering information engineering ComputingMethodologies_COMPUTERGRAPHICS Orientation (computer vision) business.industry 05 social sciences Short-time Fourier transform 050301 education Pattern recognition Computer Science Applications Control and Systems Engineering Feature (computer vision) Embedding 020201 artificial intelligence & image processing Artificial intelligence business 0503 education Software |
Zdroj: | Information Sciences. 548:191-211 |
ISSN: | 0020-0255 |
Popis: | 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. |
Databáze: | OpenAIRE |
Externí odkaz: |