融合目标增强与稀疏重构的显著性检测  

Saliency detection via object enhancement and sparse reconstruction

作　　者：郭鹏飞[1] 金秋[1] 刘万军[1] 

机构地区：[1]辽宁工程技术大学软件学院,葫芦岛125105

出　　处：《中国图象图形学报》2017年第9期1240-1250,共11页Journal of Image and Graphics

基　　金：国家自然科学基金项目(61172144);辽宁省教育厅科学技术研究一般基金项目(L2015216)~~

摘　　要：目的为了解决图像显著性检测中存在的边界模糊,检测准确度不够的问题,提出一种基于目标增强引导和稀疏重构的显著检测算法(OESR)。方法基于超像素,首先从前景角度计算超像素的中心加权颜色空间分布图,作为前景显著图;由图像边界的超像素构建背景模板并对模板进行预处理,以优化后的背景模板作为稀疏表示的字典,计算稀疏重构误差,并利用误差传播方式进行重构误差的校正,得到背景差异图;最后,利用快速目标检测方法获取一定数量的建议窗口,由窗口的对象性得分计算目标增强系数,以此来引导两种显著图的融合,得到最终显著检测结果。结果实验在公开数据集上与其他12种流行算法进行比较,所提算法对具有不同背景复杂度的图像能够较准确的检测出显著区域,对显著对象的提取也较为完整,并且在评价指标检测上与其他算法相比,在MSRA10k数据集上平均召回率提高4.1%,在VOC2007数据集上,平均召回率和F检验分别提高18.5%和3.1%。结论本文提出一种新的显著检测方法,分别利用颜色分布与对比度方法构建显著图,并且在显著图融合时采用一种目标增强系数,提高了显著图的准确性。实验结果表明,本文算法能够检测出更符合视觉特性的显著区域,显著区域更加准确,适用于自然图像的显著性目标检测、目标分割或基于显著性分析的图像标注。Objective The human visual system can acquire regions of interest for different scenes based on the visual atten- tion mechanism. Each image contains one or more salient objects. Saliency detection involves imitating the visual attention mechanism to obtain important information in an image, thereby improving the efficiency and accuracy of image processing. Saliency detection methods can be used not only in detecting a target object, but also in image annotation and retrieval, object recognition, image clipping, image segmentation, image compression, and other fields. Saliency detection is a re- search hot spot in computer vision. Although existing significant detection methods have achieved good results, several problems remain, such as the blurring of significant boundaries due to foreground and background noises. Therefore, the accuracy of saliency detection should be improved. Saliency detection methods based on pixels or regions, such as super pixels, can effectively describe the features of salient regions. However, these pixels or regions exist alone and have no real object significance ; that is, complete descriptions of objects are lacking. Objectness detection involves obtaining ob- ject information by sliding windows. We propose a saliency detection algorithm via object enhancement and sparse recon- struction （OESR） to introduce object descriptions while preserving the effective description of salient features to solve the problems of fuzzy boundaries and improve the accuracy of image saliency detection. The objectness detection method is not used to directly access windows as the final salient objects. We consider window information as an object description to en- hance the effectiveness of salient features. Method The input image is segmented by super pixels, and several super pixel regions are obtained. A central weighted color spatial distribution model is adopted. The model is based on the idea that when a wide range of colors exist, these colors are less likely to belong to a salient region.

关 键 词：显著检测 全局颜色对比 稀疏重构 误差传播 目标增强 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]