Saliency map fusion method and system

Abstract

The invention provides a saliency map fusion method and system. The saliency map fusion method comprises preparation of an annotation data set, and also comprises the following steps: carrying out image appearance-based neighbor search of a test image I in an image set D; extracting an error corresponding to the nearest neighbor image from an absolute error matrix E of the image set D to form an error matrix P; calculating an average absolute error of each detection method of a K nearest neighbor set, K being the number of neighbor images; calculating the weight of each detection method according to the average absolute error; and performing salient region extraction and fusion on the test image I by applying M detection methods. According to the saliency map fusion method and system provided by the invention, image data does not need to be trained in advance, and the problem of parameter modification caused by different training sets is avoided, and the processing method is simple, and the accuracy and efficiency of saliency region detection are effectively improved.

Description

technical field [0001] The invention relates to the technical fields of computer vision and image processing, in particular to a saliency map fusion method and system. Background technique [0002] Image saliency detection aims to find out the most important part of the image. It is an important preprocessing step in the field of computer vision to reduce computational complexity. It has a wide range of applications in image compression, target recognition, image segmentation and other fields. At the same time, it is a challenging problem in computer vision. Each of these methods has its own advantages and disadvantages. Even for the same saliency detection method, the detection effect for different pictures is also very different. Therefore, it is particularly important to obtain better saliency maps by combining the results of multiple saliency detection methods. There are some traditional saliency map fusion methods, most of which are simple summing and averaging or simp...

AI Technical Summary

Problems solved by technology

There are some traditional saliency map fusion methods, most of which are simple summing and averaging or simple multiplication and averaging of multiple saliency maps. The weights of the saliency detection methods are set to the same value, which is unreasonable in practice, because for a picture or even each pixel, the detection effects of various saliency detection methods are different, so the weights of each saliency detection method The value should also be set differently

At present, there are also some research methods for fusing multiple salient maps. For example, Mai et al. used conditional random field (CRF) to fuse multiple salient maps, and achieved good results, but the effect of the recall rate is not satisfactory.

Images