Lable feature near-duplicated video detection method based on convolutional neural network semantic classification

Abstract

The invention discloses a label feature near-duplicate video detection method based on convolutional neural network semantic classification, and aims to solve the problems of large feature storage space, low retrieval efficiency and the like in the existing near-duplicate video retrieval field. The method comprises the following steps: firstly, extracting dense semantic classification label features from a video by utilizing a deep convolutional neural network model; removing redundancy according to repeatability among the video frame label features to obtain semantic classification label features of the video; carrying out similarity matching on the feature vectors of the query video and the library video; and finally, measuring the similarity of the two videos by calculating a Jaccard coefficient so as to achieve the detection of the nearly repeated videos, wherein the two steps of video tag feature redundancy elimination and feature matching have two implementation modes of a videolevel and a frame level, namely, nearly repeated video detection based on semantic classification tag features can be achieved through two different levels of methods. According to the invention, near-repetitive video detection can be rapidly realized, and the method has certain robustness for video editing transformation and noise.

Description

technical field [0001] The invention belongs to the field of multimedia information processing, and in particular relates to a near-duplicate video detection method based on label features of convolutional neural network semantic classification. Background technique [0002] With the vigorous development of Internet technology, video, as the carrier of information, plays an increasingly important role in information expression and information transmission; and the rapid development of video capture equipment and video editing software, users can more easily obtain and edit , Share video, online video shows explosive growth. Take YouTube, the world's largest video website, as an example. Currently, more than 500 hours of videos are uploaded every minute on the website, with more than 1.8 billion monthly active users. However, in this massive video data, there are a large number of identical or similar videos. According to relevant research results, when searching based on 2...

AI Technical Summary

Problems solved by technology

[0006] The present invention solves the problems of lack of semantic features and detection efficiency in the prior art by means of deep learning

Images