An image saliency detection method based on FLIC superpixel segmentation

Abstract

The invention belongs to the technical field of image analysis, and discloses an image saliency detection method based on FLIC superpixel segmentation. The input image uses a filtering method based ona total variation model to remove texture and obtain an image containing color features. Gabor filter matrix extraction is used to filter the image, and the image containing image texture informationis obtained. The image containing color features is segmented by FLIC and the contrast value is calculated. FLIC is used to segment the image which contains texture features to calculate the contrastvalue. By using linear fusion technique, the two contrast ratios are fused linearly through weights to obtain new contrast ratios, and the salient images based on color features and texture featuresare finally obtained. The detection effect of the invention for the high-texture image is obviously improved compared with the current representative method; the method can be used in computer visiontasks.

Description

technical field [0001] The invention belongs to the technical field of image analysis, in particular to an image saliency detection method based on FLIC superpixel segmentation. Background technique [0002] At present, the existing technologies commonly used in the industry are as follows: saliency detection is a research hotspot in image processing in recent years, and it has played an important role in practical applications such as image segmentation, adaptive compression, and image retrieval. With the development of computing models, more and more saliency detection algorithms have been proposed, and the detection speed, accuracy, robustness and other indicators have been greatly improved. Although the image saliency detection technology has made great progress, in the actual application process, the complex background texture, low contrast of the target area and uneven brightness will have a great impact on the image saliency detection results. Existing methods are ma...

AI Technical Summary

Problems solved by technology

[0004] (1) Prior art 1 to prior art 6 do not consider the texture information of the image, so an accurate saliency map cannot be obtained. This scheme extracts the color feature map and texture feature map of the image respectively, and further obtains color-based feature and texture-based feature respectively. saliency map, and finally adopt a linear fusion strategy to fuse the two to obtain a more complete saliency map

[0005] (2) Existing saliency detection methods using superpixel segmentation for preprocessing generally have a low processing speed and cannot meet the requirements in some applications that require high real-time performance. The reason is that these methods use SLIC superpixels. The calculation efficiency of the method itself is relatively low, and the present invention adopts the superpixel segmentation method FLIC with the best current effect

Images