Visual Saliency Algorithm Based on Global Color Contrast and Spatial Distribution in Image

Abstract

The invention discloses a visual saliency algorithm based on global color contrast and spatial distribution in an image. The specific steps are as follows: (1) Input an original image, and pre-segment the original image into? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? N regions, 1≤i≤N, generate N pre-segmented region marker maps; (2) Calculate the color saliency value of the i-th region; (3) Calculate the color saliency value of pixel s; (4) Calculate the position saliency value of the i-th region; (5) calculate the position saliency value of pixel s; (6) calculate the color and position saliency value of pixel s, and then normalize the saliency value of the pixel, Computes a per-pixel normalized saliency value. The present invention combines the two aspects of color global contrast and spatial distribution, not only can calculate the saliency map with the same resolution as the original image, but also the salient objects in the calculated saliency map are evenly highlighted, and the background is well captured Suppression is more suitable for content-based applications such as image segmentation.

Description

technical field [0001] The invention relates to the field of computer vision, in particular to a method for calculating visual saliency in images. Background technique [0002] The calculation process of visual saliency is to simulate the process of human eyes observing the image, and then extract the area of ​​interest of human eyes, and finally obtain a visual saliency map corresponding to the degree of attention. When the human eye observes an image, it often pays attention to a relatively prominent area or image block, and these prominent areas or image blocks are called visually salient areas. The process of highlighting these visually salient regions by a certain calculation method is called visually salient region detection. In order to facilitate efficient subsequent processing of images, inspired by the attention mechanism of the human eye, we use a computer to simulate the human visual system to detect visually salient regions of the image. In many aspects such a...

AI Technical Summary

Problems solved by technology

But the disadvantage is that the resolution of the obtained visual saliency map is lower than that of the original image, resulting in the loss of original image information.

The saliency detection method proposed by Goferman (Reference: SGoferman, LZelnik-Manor, ATal.Context-awaresaliencydetection.IEEEConf.onCVPR, 2010) solves the problem of low resolution, while considering the local difference and global difference of the image, and intentionally The background area around the salient object is preserved, but Goferman's method usually produces higher saliency values ​​near the edge of the object, while the saliency value inside the object decreases, and there is still a gap in uniformly highlighting the entire visually salient object. insufficient

Images