Fuzzy Sparse Subspace Clustering for Infrared Image Segmentation

Infrared image segmentation is a challenging task, due to interference of complex background and appearance inhomogeneity of foreground objects. A critical defect of fuzzy clustering for infrared image segmentation is that the method treats image pixels or fragments in isolation. In this paper, we propose to adopt self-representation from sparse subspace clustering in fuzzy clustering, aiming to introduce global correlation information into fuzzy clustering. Meanwhile, to apply sparse subspace clustering for non-linear samples from an infrared image, we leverage membership from fuzzy clustering to improve conventional sparse subspace clustering. The contributions of this paper are fourfold. First, by introducing self-representation coefficients modeled in sparse subspace clustering based on high-dimensional features, fuzzy clustering is capable of utilizing global information to resist complex background as well as intensity inhomogeneity of objects, so as to improve clustering accuracy. Second, fuzzy membership is tactfully exploited in the sparse subspace clustering framework. Thereby, the bottleneck of conventional sparse subspace clustering methods, that they could be barely applied to nonlinear samples, can be surmounted. Third, as we integrate fuzzy clustering and subspace clustering in a unified framework, features from two different aspects are employed, contributing to precise clustering results. Finally, we further incorporate neighbor information into clustering, thus effectively solving the uneven intensity problem in infrared image segmentation. Experiments examine the feasibility of proposed methods on various infrared images. Segmentation results demonstrate the effectiveness and efficiency of the proposed methods, which proves the superiority compared to other fuzzy clustering methods and sparse space clustering methods.

I. Introduction

Clustering is a reliable technique for infrared image segmentation [1], [2], [3], [4]. Through clustering, data samples are divided into groups in terms of inter-sample similarity. When applied to infrared image segmentation, clustering methods partition areas in an image based on their features [5]. Fuzzy c-means clustering (FCM) is a classical clustering method based on fuzzy set theory. The core idea of fuzzy set theory is to determine the membership of each sample, which denotes the relationship among pixels. Owing to fuzzy set theory, FCM is widely applied in infrared image segmentation, as it is capable to tackle ambiguous object boundaries in infrared images. Generally, conventional FCM could process noise-free [6], [7], [8] and low-dimension data [9], [10] efficiently [9], [10]. Whereas, it is sensitive to noise and outliers. These shortcomings are catastrophic in infrared image segmentation, because of ubiquity of noise and intensity inhomogeneity of objects.