Image significance target detection method based on maximum neighborhood and superpixel segmentation

Abstract

The invention provides an image significance target detection method based on maximum neighborhood and superpixel segmentation, which is used for solving the technical problem of low image saliency target detection accuracy in the prior art. The method comprises the following implementation steps: 1, carrying out super-pixel segmentation on a to-be-detected image; 2, counting the occurrence frequency of each color in the to-be-detected image; 3, performing color substitution on the to-be-detected image; 4, preprocessing the image after color substitution; 5, calculating an initial saliency image of the to-be-detected image; 6, determining significance values of the K super-pixel blocks; and 7, obtaining and outputting a final saliency image. According to the invention, the accuracy of image saliency target detection is improved, the image saliency targets can be consistent and highlighted, and the method can be used for an image preprocessing process in the field of computer vision.

Description

technical field [0001] The invention belongs to the technical field of computer image processing, and relates to an image salient object detection method, in particular to an image salient object detection method based on maximum neighborhood and superpixel segmentation, which can be used in the image preprocessing process in the field of computer vision . Background technique [0002] When human beings observe an image, they usually only pay attention to a more salient part of the whole image. Therefore, when the computer simulates the human visual system, the simulation is mainly performed by detecting salient regions in the image. Image salient object detection can improve the performance of many computer vision and image processing algorithms, and can be used in research fields such as image segmentation, object recognition, and image retrieval. [0003] According to the detection principle, image saliency target detection can be divided into three categories: models b...

AI Technical Summary

Problems solved by technology

This method can provide the most eigenvalues ​​for image sub-blocks, but its defect is that the saliency detection image is obtained by weighting the difference values ​​between different sub-blocks of the image, and the salient objects in the detection image are also retained. Non-target regions, resulting in lower final saliency detection accuracy

[0005] As another example, in the article "Saliency detection using maximum symmetric surround" published by Achanta et al. on ICIP in 2010, using the color and brightness information of pixels in the image, they proposed to detect image saliency targets based on the maximum symmetric neighborhood and detect objects with Full-resolution saliency images, this method can detect salient objects, but cannot remove non-target areas, resulting in low detection accuracy

Images