Multi-scale region fusion-based salient region detection method

Abstract

The invention relates to a multi-scale region fusion-based salient region detection method. The multi-scale region fusion-based salient region detection method is characterized by including the following steps that: an optimal color gradient and a normalized gradient of an image are calculated; the image is traversed through utilizing gradient indexes, pixel pairs which satisfy a fusion threshold are fused, so that a tag image under a first scale can be obtained; an edge gradient map of the tag image is calculated; iterative calculation is performed under each scale, so that a multi-scale tag image can be obtained; a multi-scale candidate saliency map can be obtained through utilizing mutual information; and an optimal scale can be found out through utilizing geometrical information entropy, and a candidate saliency map under the optimal scale is a final saliency map. The multi-scale region fusion-based salient region detection method is simple in concept. With the multi-scale region fusion-based salient region detection method adopted, image data are not required to be trained in advance; parameters can be easily modified; high processing speed can be realized; and the efficiency and accuracy of salient region detection can be greatly improved. The multi-scale region fusion-based salient region detection method of the invention can be widely applied to computer vision and other related image processing fields.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a salient region detection method based on multi-scale region fusion. Background technique [0002] The salient area refers to the image area composed of image details with high discrimination spontaneously in the visual system. Discrimination here is a relative attribute, which depends on the degree of visual distinction between the image details and its background. The salient area detection is to reproduce how the human eye quickly focuses on these areas of interest in complex visual scenes. Therefore, the salient region detection can accurately predict the attention distribution of static and dynamic scenes under free observation, and the detection also reflects which image details of interest the human eye can find in the visual scene. Correctly extracting these key areas can greatly improve image analysis, processing efficiency and accuracy, and reduce computation...

AI Technical Summary

Problems solved by technology

These methods are simple to implement, but there are the following problems: when the image size is different, the detection results are quite different, and only the outline can be detected for the large-sized salient area; when the image size is too small, the smaller-sized target area Poor test result

Generally speaking, this method is to perform saliency detection on the sampled image, so the resolution of the obtained saliency map is low

Images