计算机应用 ›› 2018, Vol. 38 ›› Issue (3): 866-872.DOI: 10.11772/j.issn.1001-9081.2017081933

• 虚拟现实与多媒体计算 • 上一篇    下一篇

自适应融合局部和全局稀疏表示的图像显著性检测

王鑫1, 周韵1, 宁晨2, 石爱业1   

  1. 1. 河海大学 计算机与信息学院, 南京 211100;
    2. 南京师范大学 物理科学与技术学院, 南京 210000
  • 收稿日期:2017-08-09 修回日期:2017-11-03 出版日期:2018-03-10 发布日期:2018-03-07
  • 通讯作者: 王鑫
  • 作者简介:王鑫(1981-),女,安徽阜阳人,副教授,博士,主要研究方向:图像处理、模式识别、计算机视觉;周韵(1992-),女,江苏南通人,硕士研究生,主要研究方向:图像处理;宁晨(1978-),男,安徽阜阳人,讲师,硕士,主要研究方向:压缩感知;石爱业(1969-),男,江苏南京,副教授,博士,主要研究方向:图像处理、视觉计算。
  • 基金资助:
    国家自然科学基金资助项目(61603124);江苏省"六大人才高峰"高层次人才项目(XYDXX-007);江苏省"333高层次人才培养工程";教育部中央高校基本科研业务费专项资金资助项目(2015B19014)。

Image saliency detection via adaptive fusion of local and global sparse representation

WANG Xin1, ZHOU Yun1, NING Chen2, SHI Aiye1   

  1. 1. College of Computer and Information, Hohai University, Nanjing Jiangsu 211100, China;
    2. School of Physics and Technology, Nanjing Normal University, Nanjing Jiangsu 210000, China
  • Received:2017-08-09 Revised:2017-11-03 Online:2018-03-10 Published:2018-03-07
  • Supported by:
    This work is partially supported by the National Natural Science Foundation of China (61603124), the Six Talents Peak Project of Jiangsu Province (XYDXX-007), the 333 High-Level Talent Training Program of Jiangsu Province, the Fundamental Research Funds for the Central Universities (2015B19014).

摘要: 针对基于局部或全局稀疏表示的图像显著性检测方法频繁出现提取对象不完整、边界不光滑及噪声消除不干净等问题,提出自适应融合局部和全局稀疏表示的图像显著性检测方法。首先,对原始图像进行分块处理,利用图像块代替像素操作,降低算法复杂度;其次,对分块后的图像进行局部稀疏表示,即:针对每一个图像块,选取其周围的若干图像块生成过完备字典,基于该字典对图像块进行稀疏重构,得到原始图像的初始局部显著图,该显著图能够有效提取显著性目标的边缘信息;接着,对分块后的图像进行全局稀疏表示,与局部稀疏表示过程类似,不同的是针对每一个图像块所生成的字典来源于图像四周边界处的图像块,这样可以得到能有效检测出显著性目标内部区域的初始全局显著图;最后,将初始局部和全局显著图进行自适应融合,生成最终显著图。实验结果表明,提出算法在查准率(precision)、查全率(recall)及F-measure等指标上优于几种经典的图像显著性检测方法。

关键词: 显著性检测, 局部稀疏表示, 全局稀疏表示, 自适应融合, 显著图

Abstract: To solve the problems of local or global sparse representation based image saliency detection methods, such as incomplete object extracted, unsmooth boundary and residual noise, an image saliency detection algorithm based on adaptive fusion of local sparse representation and global sparse representation was proposed. Firstly, the original image was divided into a set of image blocks, and these blocks were used to substitute the image pixels, which may decrease the computational complexity. Secondly, the blocked image was represented via local sparse representation. Specifically, for each image block, an overcomplete dictionary was generated by using its surrounding image blocks, and based on such dictionary the image block was sparsely reconstructed. As a result, an initial local saliency map which may effectively extract the edges of the salient objects could be gotten. Thirdly, the blocked image was represented by global sparse representation. The procedures were similar to the above steps. The difference was that, for each image block, the overcomplete dictionary was constructed by using the image blocks from the four margins of the input image. According to this, an initial global saliency map which could effectively detect the inner areas of the salient objects was obtained. Finally, the initial local and global saliency maps were adaptively fused together to compute the final saliency map. Experimental results demonstrate that compared with several classical saliency detection methods, the proposed algorithm significantly improves the precision, recall and F-measure.

Key words: saliency detection, local sparse representation, global sparse representation, adaptive fusion, saliency map

中图分类号: