基于局部特征与全局特征的图像显著性目标检测

Image saliency target detection based on global features and local features

在采用图像谱残差分析方法获取全局特征显著性图像的基础上,利用小波变换在时域和频域具有的局部特征信息表征能力,通过对图像包含的不同特征信息进行小波变换,去除各个特征图中的冗余信息,得到图像局部特征显著部分,对两种分析方法下获得的显著图进行融合分析,获得最终的图像显著部分,并利用视觉转移机制在原图中勾画出显著性目标.实验结果分析表明,改进后的方法提高了图像显著目标检测的准确率.

The method of spectral residual analysis is adopted to get the global features＇ saliency map, and the wavelet transforms＇ local feature information representation ability in the time domain and frequency domain is used to remove redundant information and get local features highlights. The two ways are combined to get the final-saliency map and block out the saliency target. Experimental results show that the detection accuracy is improved by using the proposed method.