New non‐negative sparse feature learning approach for content‐based image retrieval. Issue 9 (4th August 2017)

• Record Type: Journal Article
• Authors: Xu, Wangming; Wu, Shiqian; Er, Meng Joo; Zheng, Chaobing; Qiu, Yimin
• Is Part Of: IET image processing. Volume 11:Issue 9(2017)
• Page Start: 724
• Page End: 733
• Publication Date: 2017-08-04
• Subjects: image retrieval -- content‐based retrieval -- image representation -- learning (artificial intelligence) -- feature extraction; spectral clustering method -- image databases -- image representation -- kMaxSum pooling -- feature pooling strategy -- NNLLC -- nonnegative locality‐constrained linear coding -- content‐based image retrieval -- nonnegative sparse feature learning approach; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2016.0726
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : One key issue in content‐based image retrieval is to extract effective features so as to represent the visual content of an image. In this study, a new non‐negative sparse feature learning approach to produce a holistic image representation based on low‐level local features is presented. Specifically, a modified spectral clustering method is introduced to learn a non‐negative visual dictionary from local features of training images. A non‐negative sparse feature encoding method termed non‐negative locality‐constrained linear coding (NNLLC) is proposed to improve the popular locality‐constrained linear coding method so as to obtain more meaningful and interpretable sparse codes for feature representation. Moreover, a new feature pooling strategy named kMaxSum pooling is proposed to alleviate the information loss of the sum pooling or max pooling strategy, which produces a more effective holistic image representation and can be viewed as a generalisation of the sum and max pooling strategies. The retrieval results carried out on two public image databases demonstrate the effectiveness of the proposed approach.