Research on Micro Video Character Recognition Based on Target Detection Technology

Abstract

With the rapid development of Internet short video platform, micro video is loved by more and more users because of its advantages such as small traffic and time period. However, the content of micro video on the Internet is complex, including much illegal and illegal content information. This research is an improved algorithm based on target detection technology and aiming at the characteristics of difficult character recognition in micro video. The algorithm combines Gabor wavelet transform algorithm and 2DPCA algorithm. Through MATLAB simulation analysis, it can be seen that the optimization algorithm proposed in this paper has better recognition rate and recognition efficiency.