韦伯-中心环绕结构的图像显著性检测模型  

Image saliency detection model with Weber's law based on center-surround structure

作　　者：林丽莉[1] 周文晖[2] 

机构地区：[1]浙江工商大学信息与电子工程学院,杭州310018 [2]杭州电子科技大学计算机学院,杭州310018

出　　处：《中国图象图形学报》2012年第10期1261-1267,共7页Journal of Image and Graphics

基　　金：国家自然科学基金项目(60902077;61102146);浙江省自然科学基金项目(Y1091074;Z1111051)

摘　　要：受韦伯定理和协作式中心环绕接收域生物模型的启发,提出一种适用于图像显著性检测的中心环绕假设,设计了一种具有圆形拓扑的中心环绕结构,并给出基于该模型的融合局部和全局特性的显著性检测算法。该算法提取各像素的中心环绕结构,以基于韦伯特性的梯度方向表征局部显著性,中心区域相对于总体均值的相对亮度差表征全局显著性,然后采用线性合并方法得到最终的显著图。检测结果及正确率-召回率评估曲线表明该算法具有良好的检测特性,并且在激活区域具有强响应,同时还能很好地抑制其他区域。Inspired by Weber＇s Law and the biological model of synergistic centersurround receptive field, we propose a centersurround hypothesis for image saliency detection and design a centersurround structure with circular topology. Based on this model, a saliency detection method fusing local and global features is proposed. It extracts the centersurround structure of each pixel, using Weber＇s Law based gradient orientation to represent local saliency, and using the relative in tensity differences of the center region against the overall mean to represent global saliency, then it gives the final saliency map by linear combination of local and global saliencies. Comparison experiments and precisionrecall curve demonstrate this detector has better performance, and has strong response in active region while inhibits other regions.

关 键 词：视觉显著性 韦伯定理 中心环绕结构 局部显著性 全局显著性 

分 类 号：TN911.73[电子电信—通信与信息系统]