New non-negative sparse feature learning approach for content-based image retrieval

• Published in: IET image processing Vol. 11; no. 9; pp. 724 - 733
• Main Authors: Xu, Wangming, Wu, Shiqian, Er, Meng Joo, Zheng, Chaobing, Qiu, Yimin
• Format: Journal Article
• Language: English
• Published: The Institution of Engineering and Technology 01.09.2017
• Subjects: content‐based image retrieval; content‐based retrieval; feature extraction; feature pooling strategy; image databases; image representation; image retrieval; kMaxSum pooling; learning (artificial intelligence); NNLLC; nonnegative locality‐constrained linear coding; nonnegative sparse feature learning approach; Research Article; spectral clustering method; nonnegative locality-constrained linear coding; feature pooling strategy; spectral clustering method; NNLLC; content-based retrieval; nonnegative sparse feature learning approach; kMaxSum pooling; feature extraction; image representation; image retrieval; learning (artificial intelligence); content-based image retrieval; image databases
• ISSN: 1751-9659; 1751-9667; 1751-9667
• DOI: 10.1049/iet-ipr.2016.0726

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.