提出一种基于视觉注意机制的彩色图像分割方法。受生物学启发,该方法模仿人类自下而上的视觉选择性注意过程,提取图像的底层特征,构造相应的显著图。根据显著图,检测出图像中的显著区域;将显著区域和背景分离,即得到图像分割结果。在多幅自然图像上进行实验,结果表明,该方法能够取得与人类视觉系统一致的分割结果。
A new approach for color image segmentation based on visual attention mechanism is proposed.Motivated biologically,this approach simulates the bottom-up human visual selective attention mechanism,extracts low-level features of the image and constructs the saliency map.According to the saliency map,the salient regions in an image are detected.The image is segmented by separating the salient regions and the background.This approach has been tested on natural images. The experimental results show this approach is consistent with human visual system.