自动化学报Issue(4)：711-724,14.DOI:10.16383/j.aas.2015.c140328
基于条件随机场和图像分割的显著性检测
Saliency Detection Based on Conditional Random Field and Image Segmentation
摘要
Abstract
The problem of sparse and unclear boundary with uneven and non-compact interior existed in the saliency region detected by most saliency detection methods. In order to solve this problem, this paper proposes a saliency detection method based on the conditional random field (CRF) and image segmentation. This method comprehensively utilizes boundary information, local information and global information to extract a variety of salient features from an image. By fusing these features into the framework of conditional random field, a coarse detection for saliency region is realized based on region labeled of saliency region and background region, and then a fine detection for saliency region is achieved through combining the result of region labeled with an interactive image segmentation method. Experimental results show that the proposed approach can clearly and accurately extract saliency regions and improve the detection precision.关键词
显著性检测/多特征融合/条件随机场/图像分割Key words
Saliency detection/multi-feature fusion/conditional random field (CRF)/image segmentation引用本文复制引用
钱生,陈宗海,林名强,张陈斌..基于条件随机场和图像分割的显著性检测[J].自动化学报,2015,(4):711-724,14.基金项目
Manuscript received May 9,2014 （）
accepted October 27,2014国家自然科学基金(61375079)资助Supported by National Natural Science Foundation of China (61375079) （61375079）
