Method for extracting image region of interest based on eye movement data and bottom-layer features

Abstract

The invention discloses a method for extracting an image region of interest based on eye movement data and bottom-layer features. On one hand, the image region of interest, namely, eye movement ROI (Region Of Interest), for reflecting human real semanteme is extracted by visual point tracking experimental data of an eye movement instrument, and on the other hand, the image region of interest, namely, feature ROI, in a general sense is extracted in a form of bottom-layer feature weighted combination, and weight combination with highest similarity, namely, optimal weight, is found out by similarity analysis of the feature ROI and the eye movement ROI. The region of interest of other image of the same type, extracted by using the weight, can more comply with the semantic demands of users.

Description

technical field [0001] The invention belongs to the technical field of image recognition, and relates to an image region-of-interest extraction method based on eye tracker experimental data and underlying features. Background technique [0002] With the rapid development of multimedia technology and Internet technology, the image data generated in human life and scientific experiments is expanding rapidly, and it is becoming more and more difficult for people to process image information. Therefore, how to store, express, organize and manage digital image data and how to quickly and accurately find the information you need from massive, disordered pictures are prominent problems in many current application fields. The study found that the main information of the image is often only concentrated in a few areas, and often only these key areas can give people a novel feeling, thereby attracting people's attention. These key areas are the image area of ​​interest. Find out the ...

AI Technical Summary

Problems solved by technology

[0006] In the existing methods for extracting image regions of interest, they are basically realized by using the underlying features such as color, brightness, and direction, but they do not consider the difference in the degree of influence of each underlying feature on the region of interest and the actual observation results of the user. the feedback

When dealing with different types of pictures, some pictures may obviously have color features as the main factor, and some pictures may have the most influential influence on brightness features. If each feature is only considered with equal weight, the extracted region of interest will not be obvious.

Images