Multimedia file identity recognition method based on feature code

Abstract

The invention discloses a multimedia file identity recognition method based on a feature code. The method comprises the following steps that 1, a client collects an original multimedia file and initiates a recognition request; 2, the processor receives a multimedia file identification request from a client and identifies the format of the multimedia file; 3, feature points of the pictures, the audios and the video files are detected and extracted; 4, the client collects a multimedia file for matching and sends a request to the processor; 5, the processor receives the request and executes the step 2 and the step 3 on the matched multimedia file; and 6, the feature points of the original multimedia file are compared with the feature points of the matched multimedia file by the processor, thematching degree is calculated, and a result is fed back to the client. The method is high in efficiency, complex multimedia comparison is simplified into simple stable feature code comparison, and the time of manual or machine comparison is shortened.

Description

technical field [0001] The invention relates to the field of multimedia file identification, in particular to a feature code-based identification method for multimedia files. Background technique [0002] Internet multimedia files include pictures, text, sound, video, etc., because they exist on the network carrier in the form of digital codes, so copying and dissemination becomes very simple and fast. In the process of dissemination, more and more infringement disputes have arisen. Therefore, how to prevent the occurrence of infringement cases and how to quickly identify infringements is a problem to be solved on the basis of existing technologies. [0003] As we all know, neither instant messaging tools (such as WeChat) nor information interactive websites (such as Weibo) can fundamentally eliminate the source of image infringement. After all, the data volume of multimedia files is huge, and it is impossible to effectively compare them one by one and notify the infringeme...

AI Technical Summary

Problems solved by technology

In the process of dissemination, more and more infringement disputes have arisen, so how to prevent the occurrence of infringement cases, and how to quickly identify infringements is a problem to be solved on the basis of existing technologies

[0003] As we all know, neither instant messaging tools (such as WeChat) nor information interactive websites (such as Weibo) can fundamentally eliminate the source of image infringement

After all, the data volume of multimedia files is huge, and it is impossible to effectively compare them one by one and notify the infringement risk before the infringement occurs.

[0004] Traditional multimedia requires a lot of storage space, the cost is huge, and files are distributed in every corner of the network, resulting in a very long comparison period

Images