Method for detecting image significance

Abstract

The invention belongs to the technical field of detection of image significance, which is characterized in that the significance target of any image can be detected, and relates to relevant knowledge of image processing. The method comprises the following steps of: firstly, over-segmenting an image into super pixels, and performing Harris interest point detection to form a convex hall; secondly, performing edge detection on the image and calculating the edge weight map of the image; thirdly, measuring color space information by using the edge weight image to obtain a prior image; fourthly, performing soft segmentation based on the prior image to obtain an observation likelihood probability; and lastly, combining the prior image with the observation likelihood probability by using a Bayesian framework to obtain a significance detection result. The method has the beneficial effects that background noise can be well eliminated, a high-brightness image target is smoothened, the situations of target color and background similarity, large targets and complex backgrounds which are always difficult to solve in significance detection can be handled, and the method can be well applied to ordinary images.

Description

technical field [0001] The invention belongs to the technical field of image saliency detection, can detect a saliency target in any image, and relates to relevant knowledge of image processing. Background technique [0002] With the continuous development of image processing technology, image saliency detection, as an image preprocessing method, is widely used in many fields such as image compression, image classification and image segmentation. [0003] Saliency detection is mainly divided into two categories: top-down and bottom-up. The top-down method requires certain prior knowledge. A certain sample set is given for training to obtain a rough image model, and then the test image is judged by fitting the model. Although the top-down method can process more complex images, due to the limitation of the training set, the scalability of this type of method is poor. The bottom-down method processes the color, brightness, texture and other information of the image to find t...

AI Technical Summary

Problems solved by technology

First of all, most of the existing image saliency methods are generally easy to detect the target, but they are concentrated on the edge of the image, and it is difficult to uniformly highlight the entire salient target. This is caused by the mechanism of the center-surrounding method itself. The various features in the center and surroundings have the largest difference and are easy to highlight, while the center part of the target has a small difference because the surrounding windows are still targets, and it is difficult to highlight

Secondly, due to the unknown size and position of the target, it is necessary to use the sliding window mechanism to search the entire image, which increases the amount of calculation and redundancy.

Finally, when the background is complex and contains many edges and color differences, the existing bottom-up methods only rely on low-level visual information, the background will have a greater impact on target detection, and many irrelevant low-level Responds to visual cues and tends to lose information on targets of interest

Images