Face and name aligning method and system facing to cross media news retrieval

Abstract

The invention belongs to the technical field of cross-media information retrieval and particularly relates to face and name aligning method and system based on image characteristics and text content in cross media news retrieval. In the invention, four main algorithms are included, and are name importance assessment algorithm, multimode information discovery algorithm based on web excavation, face set cohesion algorithm and multimode aligning combination optimization algorithm. In the invention, the related image characteristics and text content processing method is used, meanwhile, relative mathematical model is built, optimization to new picture search is performed, and through multi-grade and deep-level text content analyses and effective face-name alignment evaluation mechanism, and combination optimization at the aim of problems can be achieved. According to the invention, a great significance to efficient image retrieval performed under the consideration of high level semantic information of images and on the basis of large-scale and multifarious new image can be played, the retrieval relativity can be enhanced, the user experience is enhanced, and the wide application value is played in the field of medium information retrieval.

Description

technical field [0001] The invention belongs to the technical field of cross-media information retrieval, and in particular relates to a specific media-multimodal news cross-media retrieval method and system. Background technique [0002] With the popularization of the network and the popularization of image equipment, the rapidly enhanced digital acquisition technology and storage delivery capabilities have led to an explosive increase in online and offline image data, especially those news image resources with text annotations. Because the sources of such information are becoming more and more abundant, it is very important to implement more effective retrieval, organization and analysis of news image resources [1] . [0003] On the one hand, since news images and their corresponding text annotations are usually described on the subject of people, this makes it more urgent for users to query news images related to a specific person by using a complete and effective retrie...

AI Technical Summary

Problems solved by technology

However, different news face images belonging to the same person may be very different due to many factors such as light intensity, occlusion degree, face angle, etc.

Therefore, it is not sufficient to measure the overall correlation of each retrieved face set by directly measuring the similarity between these face visual features.

[0016] (4) Since aligning faces and names in the entire data set is different from finding the face image corresponding to a specific person, it is due to the fact that the problem to be solved becomes more complex as the data set increases

Therefore, these methods cannot guarantee to obtain a satisfactory final solution within a relatively satisfactory time cost to a large extent.

Images