Visual feature coding based on heterogeneous structure fusion for image classification

• Published in: Information fusion Vol. 36; pp. 275 - 283
• Main Authors: Lin, Guangfeng, Fan, Caixia, Zhu, Hong, Miu, Yalin, Kang, Xiaobing
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.07.2017
• Subjects: Heterogeneous structure fusion; Image classification; Images structure; Words structure; Images structure; Words structure; Heterogeneous structure fusion; Image classification
• ISSN: 1566-2535; 1872-6305
• DOI: 10.1016/j.inffus.2016.12.010

•High-order topology is used for the description of words structure.•Image structure is represented based on the local feature.•The nonlinear relationship of heterogeneous structure is revealed for classification.•Heterogeneous structure fusion shows the better performance for feature encoding. The relationship between visual words and local feature (words structure) or the distribution among images (images structure) is important in feature encoding to approximate the intrinsically discriminative structure of images in the Bag-of-Words (BoW) model. However, in recently most methods, the intrinsic invariance in intra-class images is difficultly captured using words structure or images structure for large variability image classification. To overcome this limitation, we propose a local visual feature coding based on heterogeneous structure fusion (LVFC-HSF) that explores the nonlinear relationship between words structure and images structure in feature space, as follows. First, we utilize high-order topology to describe the dependence of the visual words, and use the distance measurement based on the local feature to represent the distribution of images. Then, we construct the unitedly optimal framework according to the relevance between words structure and images structure to solve the projection matrix of local feature and the weight coefficient, which can exploit the nonlinear relationship of heterogeneous structure to balance their interaction. Finally, we adopt the improving fisher kernel(IFK) to fit the distribution of the projected features for obtaining the image feature. The experimental results on ORL, 15 Scenes, Caltech 101 and Caltech 256 demonstrate that heterogeneous structure fusion significantly enhances the intrinsic structure construction, and consequently improves the classification performance in these data sets.