Image retrieval method based on visual saliency fusion

Abstract

Provided is an image retrieval method based on visual significant integration. A retrieval object is color images. The image retrieval method comprises a training process and a testing process. The training process comprises step 1, building a visual word dictionary: orderly analyzing all images in a training image set so as to set up the visual word dictionary for subsequent retrieval; step 2, utilizing a fusion algorithm of image visual saliency characteristics to obtain a visual saliency picture and obtaining a foreground target picture and a background area picture by partitioning of the saliency picture; step 3, respectively extracting image color characteristics and image texture characteristics of the foreground target picture and the background area picture; step 4, counting a visual word distribution histogram of each picture in a database based on operation of step 1. The testing process also comprises the step 5 of retrieving testing images. The invention provides the image retrieval method based on visual significant integration which is good in partitioning effect and high in retrieval performance.

Description

technical field [0001] The invention relates to an image retrieval method, in particular to an image retrieval method based on visual salience fusion, and belongs to the field of content-based image retrieval. Background technique [0002] With the development of multimedia technology, the number of digital images has shown a geometric growth. How to quickly and accurately find the resource requested by the user in the vast image resources is also in front of people. [0003] Content-based image retrieval technology allows users to input a picture to find other pictures with the same or similar content, which represents the mainstream development trend of image retrieval technology. [0004] Josef Sivic et al. proposed the bag-of-words model in 2006. Its core idea is to detect some key points in the whole image, and then extract the local features of these key points, and then these local features are quantified as "visual words". In this way, each image can be represente...

AI Technical Summary

Problems solved by technology

[0007] In order to overcome the disadvantages of poor segmentation effect and low retrieval performance of existing image retrieval methods, the present invention provides an image retrieval method based on visual saliency fusion with good segmentation effect and high retrieval performance, using the saliency fusion algorithm The fusion of different saliency models can improve the effect of image segmentation, thereby improving the performance of image retrieval

Images