TY - JOUR A2 - Kim, Wonjun AU - Sima, Haifeng AU - Mi, Aizhong AU - Wang, Zhiheng AU - Zou, Youfeng PY - 2016 DA - 2016/10/27 TI - Objectness Supervised Merging Algorithm for Color Image Segmentation SP - 3180357 VL - 2016 AB - Ideal color image segmentation needs both low-level cues and high-level semantic features. This paper proposes a two-hierarchy segmentation model based on merging homogeneous superpixels. First, a region growing strategy is designed for producing homogenous and compact superpixels in different partitions. Total variation smoothing features are adopted in the growing procedure for locating real boundaries. Before merging, we define a combined color-texture histogram feature for superpixels description and, meanwhile, a novel objectness feature is proposed to supervise the region merging procedure for reliable segmentation. Both color-texture histograms and objectness are computed to measure regional similarities between region pairs, and the mixed standard deviation of the union features is exploited to make stop criteria for merging process. Experimental results on the popular benchmark dataset demonstrate the better segmentation performance of the proposed model compared to other well-known segmentation algorithms. SN - 1024-123X UR - https://doi.org/10.1155/2016/3180357 DO - 10.1155/2016/3180357 JF - Mathematical Problems in Engineering PB - Hindawi Publishing Corporation KW - ER -