Extraction method of visual salient regions based on multiscale relative entropy

Abstract

The invention discloses an extraction method of visual salient regions based on multiscale relative entropy. The extraction method of the visual salient regions based on the multiscale relative entropy comprises extracting different global color feature characteristic patterns and direction characteristic patterns from input images, carrying out gaussian pyramid decomposition and multiscale normalization on the global color feature characteristic patterns and the direction characteristic patterns, respectively computing color partial relative entropy and direction partial relative entropy of respective feature space, respectively normalizing results of the different feature space, carrying out linearity superposition of the results of the different feature space, linearly adding color saliency maps and direction saliency maps together, carrying out two-dimensional gaussian smoothing, and therefore extracting visual salient regions. Compared with a traditional method, the extraction method of the visual salient regions based on the multiscale relative entropy takes a full account of color features and direction features reflecting global significance and relative entropy reflecting partial novelty, adopts a method of multiscale analysis, and has the advantages of being effective and reliable. The extraction method of the visual salient regions based on the multiscale relative entropy is capable of being used for self-adaption compressed sampling and target detection of natural images, remote sensing images and the like, and is wide in application prospect of lowcost imaging devices.

Description

technical field [0001] The invention relates to an image processing and target recognition method, in particular to a relative entropy-based method for extracting visually significant regions. Background technique [0002] With the development of information technology, the extraction and compression of information has attracted more and more attention. 80% of the external information perceived by humans comes from vision. In the face of huge visual information input, the reason why the human visual system can process quickly and effectively is because there is a difference evaluation process in the early stage of human visual signal processing, which will perceive some different Stimulus signals (novelty features) are extracted to form salient regions and assigned to limited visual attention resources. Because the calculation of salient regions has a wide range of practical application backgrounds in the fields of object detection, image compression, and image search, how...

AI Technical Summary

Problems solved by technology

The specific performance is: most of the salient areas output by the model are concentrated at the edge of the image or where the brightness changes sharply, indicating that the local feature contrast plays a leading role in the calculation of saliency, that is, the competition between the same type of basic features is mainly considered. , while factors such as the environmental context information where the features are located, and the spatial frequency selection of similar features are not well reflected

Images