Improved super-pixel-based image significance detection method

Abstract

The present invention discloses an improved super-pixel-based image significance detection method. The method comprises the following steps: firstly, segmenting an original image into super-pixels consistent in color and texture based on the simple and linear iterative clustering super pixel segmentation algorithm; secondly, for the image super-pixel segmentation result, calculating the initial saliency map of the original image based on the sparse representation theory; thirdly, for the image super-pixel segmentation result, calculating the center-edge weight map of the original image based on the center-edge idea; fourthly, for the image super-pixel segmentation result, clustering the super-pixels based on the normalized theory so as to obtain a plurality of clustering areas; fifthly, based on the above result, calculating the final saliency map of the original image. According to the technical scheme of the invention, compared with the traditional super-pixel-based image saliency detection method, the problems, including the fuzzy boundary of a saliency object, the inhibited interior of the saliency object and the like, can be solved. The saliency object can be highlighted more uniformly. Meanwhile, the background is effectively suppressed, so that a better detection result is obtained.

Description

technical field [0001] The invention relates to an image visual saliency detection method, in particular to an improved superpixel-based image saliency detection method, which belongs to the technical field of computer vision. Background technique [0002] With the continuous development of information technology, people have a large number of data resources. Among them, image resources have experienced an unprecedented growth rate due to their intuition, but the resulting information redundancy has also become a major problem in image processing. Visual saliency is a very important part of human vision. It highlights the most interesting (saliency) target by filtering the redundant information where the human eye can reach, thereby reducing the amount of follow-up information processing. At present, image saliency detection has a wide range of applications in the fields of image and video compression, image retrieval, object detection and recognition, etc. [0003] Accord...

AI Technical Summary

Problems solved by technology

Among them, the classical algorithms such as Itti, GBVS and SR are relatively easy to implement, and can also produce clearer saliency maps, but they show great sensitivity to high-frequency parts such as image edges or noise, so significant The image always tends to highlight the outline of the target boundary, while the interior of the target is often suppressed

Algorithms based on sparse representation can define image saliency through reconstruction error, but this method inevitably loses some relevant information inherent in the image, thus making the detected salient objects inaccurate

Images