Video feeling content identification method based on fuzzy comprehensive evaluation

Abstract

The invention belongs to the field of video content analysis, and in particular relates to a video feeling content identification method based on fuzzy comprehensive evaluation. The prior video feeling content identification method is insufficient in considering the problem of fuzzy attribute of feeling. Aiming at the defects existing in the prior art, the method first uses a fuzzy comprehensive evaluation model in fuzzy theory in the video feeling content identification. Compared with the prior art, the method sufficiently considers the fuzzy attribute of the video feeling content, expresses video clip content by a high-level characteristic vector closely related to feeling based on the fuzzy comprehensive evaluation model, and researches the video feeling content identification in high level; and further, the method adopts an artificial neural network (ANN) to simulate a human feeling response system and identify the video clip to induce basic feeling types generated by audiences. Experiment results verify the effectiveness and feasibility of the method in video feeling content identification.

Description

technical field [0001] The invention belongs to the field of video content analysis, in particular to a video emotional content recognition method based on fuzzy comprehensive evaluation. Background technique [0002] With the development of multimedia technology and network technology, digital video has gradually become the main media form of modern information system. In the massive video data and fast-paced living environment, people have no time or interest to watch all the video files one by one, and often only look for interesting, exciting or scary videos or video clips according to their personal hobbies , these characteristics indicate that people need a personalized emotional video application service technology. Since Professor Picard proposed the concept of "affective computing", video affective content computing has been considered by many scholars as an effective way to realize personalized video service technology (Personalization Service Technology) and shor...

AI Technical Summary

Problems solved by technology

The problem with this type of method is that most of them consider the issue of emotional content from the low-level feature level, but people cannot reconstruct the emotional type induced by the shot or scene based on the low-level features, that is, there is an "emotional gap" between them, so , directly building a bridge model between low-level features and emotional space is difficult to solve the "emotional gap" problem, and the recognition accuracy (between 50% and 71%) cannot meet people's requirements

However, due to the fuzzy property of video emotional content, none of the proposed methods take this property into account

Images