频域多尺度图像显著区域提取方法  

Multi-scale image salient region extraction based on frequency domain

作　　者：杨大伟[1] 宋程程[1] 李松江 李丹[1] 

机构地区：[1]哈尔滨工程大学信息与通信工程学院 [2]93199部队理论训练系

出　　处：《计算机应用》2014年第6期1731-1734,共4页journal of Computer Applications

基　　金：黑龙江省科技攻关项目(GC12A305);中央高校自由探索计划项目(HEUCF130801)

摘　　要：针对显著区域提取算法中不能保留图像边缘及内部细节不充实等问题,提出一种基于频域的多尺度提取方法。对图像在不同分辨率尺度下进行傅里叶变换并计算剩余频谱,以此去除冗余得到显著信息,经反变化归一化得到显著图像。仿真实验结果表明所提出方法可行有效,具有良好的视觉效果,在保留显著区域边缘的同时能均匀突出整个显著目标,在受试者工作特性曲线下面积(ROC)评价方法上也取得了较好的实验结果。To overcome the salient extraction results cannot preserve edge and enrich the inner details when extracting image salient region, a new multi-scale extraction approach based on frequency domain was proposed. In order to remove redundant information and get the innovation, the image was Fourier-transformed to get the spectral residual on multiple resolutions. Then normalization processing was applied to obtain the final saliency image. The simulation results show that the proposed method has good visual effect, which can keep the edges of salient region and highlight the whole significant target uniformly at the same time. The area under Receiver Operating Characteristic （ROC） curve of these results also has satisfied performance.

关 键 词：显著区域 频域 提取方法 多尺度 剩余频谱 

分 类 号：TN911.7[电子电信—通信与信息系统]