基于颜色和方向特征区域对比度的显著性检测模型

Saliency Detection Model Based on Region Contrast of Color and Orientation

视觉显著性检测是很多计算机视觉任务的重要步骤,提出了一种基于颜色、方向特征和空间位置关系相结合的区域对比显著性检测算法.首先用基于图论的算法将图像分割成若干区域,结合区域间颜色特征和空间对比度计算出颜色显著图.同时采用基于纹理特征的算法分割图像,通过方向特征和空间对比度得到方向显著图.最后将二者结合得到最终显著图.在国际现有公开测试集上进行仿真实验,并与其它显著性检测方法进行对比,检测结果更加准确、合理,证明此算法切实可行.

Saliency detection is an important step in many computer vision tasks. A region contrast saliency estimation algorithm based on color and orientation contrast of the segmented regions is proposed. First of all, the input image is segmented into regions using the algorithm of graph-based image segmentation, then define the color saliency for each region as the weighted sum of the region＇s contrasts to all other regions in the image. Meanwhile, we segment the image into regions using the algorithm of texture segmentation, then compute the orientation saliency for each region as the weighted sum of the region＇s contrasts to all other regions in the image. Finally, the saliency map of the input image is obtained by combining color saliency map and orientation saliency map, so the salient object is located and extracted. Our algorithm outperformed existing saliency detection methods when evaluated using the publicly available data sets. The results show that the proposed algorithm is more reasonable and effective.