基于谱残差和多分辨率分析的显著目标检测

根据人类视觉系统的特点，提出一种融合谱残差和多分辨率分析的显著目标检测方法。该方法通过在不同尺度上计算图像的亮度、颜色以及方向特征的谱残差，构建多分辨率显著性图谱序列，然后用线性插值方法将不同分辨率的特征显著图叠加得到3个特征显著图，再利用k均值聚类算法将每个特征显著图聚为两类，选择聚类中心距离最大的特征显著图作为最终的显著图，最后经过动态阈值处理获得图像的显著目标区域。基于自然图像的显著目标检测实验结果表明，该方法具有较强的稳定性和实用性，得到较为满意的检测结果。

Detecting salient objects based on spectral residual and multi-resolution

According to the characteristics of human visual system, a salient object detection method based on spectral residual and multi-resolution is proposed. We first compute the spectral residual of three features i.e. intensity, color and orientation under different scales to build a series of multi-resolution saliency maps, which can be combined through linear interpolation to generate three feature-saliency maps. Then we use k-means clustering for binary clustering and select the feature-saliency map with the largest distance between two centroids. Finally we apply dynamic threshold segmentation to get salient regions in an image. The experimental results on natural images show that the new algorithm is stable and practical, and we achieve satisfied results.