Collaborative filtering-based teaching video labeling method

Abstract

The invention discloses a collaborative filtering-based teaching video labeling method. The collaborative filtering-based teaching video labeling method mainly solves the shortcoming of the low accuracy of teaching video labeling in the prior art. The method is implemented through the steps of inputting a teaching video and performing caption key frame extraction on the teaching video according to captions to obtain D key frames; performing caption extraction on the D key frames through optical character software and performing text correction and deleting on obtain captions to obtain D text documents; performing shot segmentation on the teaching video by combining the D text documents with a Gibbs sampler to segment the teaching video into M shots; labeling a part of the M shots, computing the cosine similarity between the labeled shots and unlabeled shots through a collaborative filtering method, and selecting five words with the highest cosine similarity to label the unlabeled shots. The collaborative filtering-based teaching video labeling method takes the caption information in the teaching video into consideration, thereby effectively describing the teaching video, improving the labeling accuracy of the teaching video and being applicable to video teaching.

Description

technical field [0001] The invention belongs to the technical field of image processing, and further relates to a video labeling method in the technical field of pattern recognition, which can be used in network teaching. Background technique [0002] With the rapid development of Internet technology and multimedia technology, learning methods based on online learning platforms have gradually become an important way to effectively supplement traditional classroom learning. However, thousands of teaching videos are uploaded to the Internet every day and every hour. How to efficiently and quickly search for the videos that learners need in these massive teaching videos is an urgent research topic. The most commonly used method is to tag videos, which can effectively help online learning users find the desired videos quickly and efficiently. [0003] Existing video annotation methods are generally divided into three categories: manual annotation, rule-based annotation, and mac...

AI Technical Summary

Problems solved by technology

However, the current video annotation method based on machine learning is based on the visual features of the video, such as color, shape, texture, etc., and the scene of the teaching video is uniform, and the difference in visual features is not obvious, so the video annotation method based on machine learning When labeling the teaching video, the labeling accuracy is not high

Images