Significant object segmentation method based on adaptive three threshold values

Abstract

The invention discloses a significant object segmentation method based on adaptive three threshold values, and the method comprises the steps: firstly calculating the significance value of each pixel in a color image through a regional contrast algorithm, and generating significance maps in the same size; secondly carrying out statistics to obtain a significance histogram, finding a threshold value to preliminarily classify the significance maps into two classes through an adaptive three-threshold-value method, enabling the difference between the two classes to be maximum, finding the other two threshold values to finely classify the significance maps into four classes, and enabling the difference among the four classes to be maximum. The method enables the pixels of the significance maps to be classified into four types of seed points according to the obtained three threshold values, replaces manual interaction with the seed points to carry out the initialization of a GrabCut algorithm, and obtains a segmentation result. The method provided by the invention obtains the seed points from the significance maps through adaptive three threshold values, and effectively improves the significant object segmentation effect.

Description

technical field [0001] The invention belongs to the field of computer technology, and relates to saliency analysis and salient object segmentation of color images, and also relates to a threshold value generation method of a saliency map, in particular to a salient object segmentation method based on adaptive three thresholds. Background technique [0002] Image segmentation refers to the process of dividing the original image into foreground objects and background, which mainly uses information such as color, texture, shape, and gradient of the image. Since more attention is paid to the foreground objects in the image during image analysis and processing, segmentation technology has a wide range of applications in image classification, scene understanding, image editing and other fields. [0003] There are three types of traditional image segmentation: learning-based segmentation, human-interaction-based segmentation, and automatic segmentation. Learning-based segmentation...

AI Technical Summary

Problems solved by technology

[0006] The problem to be solved by the present invention is: most of the existing automatic segmentation methods based on saliency map use binarization to extract visually salient information from the saliency map to assist the subsequent image segmentation process, and simple binarization makes the saliency map A large amount of information in can not be fully utilized, and the segmentation method has many limitations

Images