Towards fusing fuzzy discriminative projection and representation learning for image classification. (September 2022)

• Record Type: Journal Article
• Authors: Wang, Yun; Li, Zhenbo; Li, Fei; Yang, Pu; Yue, Jun
• Is Part Of: Engineering applications of artificial intelligence. Volume 114(2022)
• Publication Date: 2022-09
• Subjects: Image classification -- Subspace projection -- Sparse representation -- Fuzzy weight matrix -- Discriminative information preservation; Engineering -- Data processing -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Ingénierie -- Informatique -- Périodiques; Intelligence artificielle -- Périodiques; Systèmes experts (Informatique) -- Périodiques; Artificial intelligence; Engineering -- Data processing; Expert systems (Computer science); Periodicals; 620.00285
• DOI: 10.1016/j.engappai.2022.105137
• Languages: English
• ISSNs: 0952-1976

Abstract

Abstract: The fuzzy and indistinguishable data affected by complex and variable factors lead to the inferior recognition performance, which is hard to avoid in data acquisition. Subspace projection is widely used in extracting low-dimensional important features for image processing task. However, many existing methods rarely explore on the fuzziness and uncertainty of visual data, while lack sufficient mining of prior knowledge. In this work, we propose a novel fuzzy discriminative projection and representation learning (FDPR) method for image classification. Specifically, the fuzzy weight matrix with label information is designed in the data reconstruction to generate more specific sparse constraint on representation coefficients. In addition, low-rank and l 2, 1 norm constraints are introduced to enhance the robustness of the algorithm. Finally, we combine a classification regression term with the representation coefficients carrying discriminative information for the subspace projection learning, thus fully utilizing data label information and eventually benefiting the subspace to be more distinguishable. The experimental results on several datasets show that our proposed model performs well with effectiveness and robustness surpassing other state-of-the-art approaches.