Accurate target segmentation method based on color significance and Gaussian model

Abstract

An accurate target segmentation method based on color significance and a Gaussian model is disclosed. The method is characterized by firstly, clustering image pixels in a Lab color space through a GMMalgorithm; then, using a SSIM image similarity algorithm to merge sub-Gaussian models, and selecting a target sub-Gaussian model as a foreground through prior color information; and then, using a CRFalgorithm to optimize a significance region and obtaining an accurate segmentation boundary. In the invention, aiming at a characteristic that an object may not accord with center and boundary priorduring significance detection, a significance object detection method based on color prior is provided. The pixels are clustered directly through the Gaussian mixture model and the center and boundaryprior is not used; the Gaussian mixture model is used to ensure that an accurate and stable boundary is acquired; the significance area located at the boundary can be detected; and compared with a traditional significance detection algorithm, the method has higher accuracy.

Description

technical field [0001] The invention belongs to the technical field of computer vision, is used for segmenting salient objects in images, and is an accurate target segmentation method based on color saliency and a Gaussian model. Background technique [0002] The human visual attention mechanism has the function of selectively processing visual images. Introducing this mechanism into image processing has many applications, including target detection, salient region extraction, etc. This selective attention mechanism can make the visual information Processing is faster. Research on visual psychology shows that the attention mechanism includes two processes, namely, a fast bottom-up data-driven process and a slow top-down goal-driven process, which is similar to the human visual attention mechanism, and saliency detection The algorithm is also divided into bottom-up and top-down. The bottom-up predicts the visual gaze point model according to the local features of the image, ...

AI Technical Summary

Problems solved by technology

In addition, the GC (global cues) algorithm proposed by Cheng M M [6] The Gaussian Mixture Model GMM (Gaussian Mixture Model) is used to detect salient objects, but GC uses GMM to divide the RGB color model, which has a poor effect on pixel clustering, and the obtained classification boundaries are blurred, and the sub-Gaussian model is merged bad in most cases

Classic GrabCut algorithm [7] The Gaussian model is also used to model the foreground and background images, and achieved good results, but the GrabCut algorithm requires the user to set the initial foreground and background areas

All of the above are general salient object detection algorithms. At present, there is no salient object detection algorithm for color prior. Based on color prior, the detection accuracy of salient objects can be improved.

Images