Video superpixels generation through integration of curvelet transform and simple linear iterative clustering

Abstract

Superpixel generation finds wide variety of applications in the field of image processing, particularly brain tumour detection, human body pose estimation, person re-identification as a pre-processing step. In this paper, we present a novel superpixel segmentation approach through integration of curvelet transform and conventional Simple Linear Iterative Clustering (SLIC) for image and video. The proposed algorithm follows a two-step framework, clustering in curvelet and spatial domain separately. It performs conventional Simple Linear Iterative clustering on curvelet coefficients obtained at different decomposition levels of R, G, B components as well as directly on R, G, B components to get initial boundaries of superpixels. We obtain final boundaries of superpixels by taking the high probable boundaries from the initial formed boundaries. By incorporation of curvelets in five different scales the proposed method is capable of generating superpixels with high boundary adherence even in the presence of background change, object motion and noise. Superpixels generated by the proposed method are homogeneous in regions of complex texture and weak boundaries. The method has been tested on different images taken from Berkeley segmentation dataset and frames of several other videos. The algorithm under study is evaluated in terms of ten evaluation parameters: boundary recall, boundary precision, quality percentage, detection percentage, accuracy, Jaccard index, specificity, figure of merit, structural content, achievable segmentation accuracy. The results are tabulated, shown graphically and discussed in detail. The critical analysis of results show sound performance of the proposed method over other state-of- art methods.