Effective texture classification by texton encoding induced statistical features. Issue 2 (February 2015)

• Record Type: Journal Article
• Authors: Xie, Jin; Zhang, Lei; You, Jane; Shiu, Simon
• Is Part Of: Pattern recognition. Volume 48:Issue 2(2015:Feb.)
• Page Start: 447
• Page End: 457
• Publication Date: 2015-02
• Subjects: Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2014.08.014
• Languages: English
• ISSNs: 0031-3203

Abstract

<abstract abstract-type="author" id="ab0005"> <title id="sect0005">Abstract</title> <sec> <p id="sp0090">Effective and efficient texture feature extraction and classification is an important problem in image understanding and recognition. Recently, texton learning based texture classification approaches have been widely studied, where the textons are usually learned via <italic>K</italic>-means clustering or sparse coding methods. However, the <italic>K</italic>-means clustering is too coarse to characterize the complex feature space of textures, while sparse texton learning/encoding is time-consuming due to the <italic>l</italic><sub>0</sub>-norm or <italic>l</italic><sub>1</sub>-norm minimization. Moreover, these methods mostly compute the texton histogram as the statistical features for classification, which may not be effective enough. This paper presents an effective and efficient texton learning and encoding scheme for texture classification. First, a regularized least square based texton learning method is developed to learn the dictionary of textons class by class. Second, a fast two-step <italic>l</italic><sub>2</sub>-norm texton encoding method is proposed to code the input texture feature over the concatenated dictionary of all classes. Third, two types of histogram features are defined and computed from the texton encoding outputs: coding coefficients and coding residuals. Finally, the two histogram features are combined for classification via a nearest subspace classifier. Experimental results on the CUReT, KTH_TIPS and UIUC datasets demonstrated that the proposed method is very promising, especially when the number of available training samples is limited.</p> </sec> </abstract>