Information fusion-based hidden Markov salient region detection method

Abstract

The invention relates to an information fusion-based hidden Markov salient region detection method. The method of the invention can be applied to target region detection and recognition in a complex background. The information fusion-based hidden Markov salient region detection method is characterized by comprising the following steps that: firstly, three color contrast channels of an image are calculated; secondly, final tag images of the channels are calculated through maximum posteriori probability iterative calculation; salient images of the channels can be obtained through utilizing a tag class with maximum mutual information; and finally, information quantity of communicated regions in the three channels, which is larger than redundant information, is added together and is normalized, so that a final saliency image can be obtained. According to the information fusion-based hidden Markov salient region detection method of the invention, prior information of the image is fully utilized with data details preserved, and therefore, problems brought by region color information missing can be solved, and a wide salient region can be quickly focused without pre-training required.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a hidden Markov salient region detection method based on information fusion. Background technique [0002] Salient region detection is to detect the image regions that attract the observer's attention most from complex natural scenes. These regions can bring strong stimulation to the human eye, so that the visual system can allocate limited perceptual resources in an effective way. At present, salient region detection is widely used in many image processing fields such as adaptive compression and scaling, unsupervised image segmentation, and object recognition. Therefore, it is of great practical value to study salient region detection methods. [0003] Some of the main methods for salient region detection at present: [0004] The SUN method was proposed by Christopher Kanan et al. in "Robust Classification of Objects, Faces, and Flowers Using Natural Image Statistics"...

AI Technical Summary

Problems solved by technology

However, this method lacks the use of prior knowledge of salient areas of the image. Salient area detection is for understanding, but the ideal detection result requires the result of understanding as prior knowledge, so salient area detection is an ill-conditioned problem. This method ignores Considering this kind of pathological problem, as the image scene becomes more complex, its detection accuracy also drops sharply

Images