Research On Chinese Video Subtitle Detection Based On Deep Learning

In the era of big data,faced with the huge amount of video image data,it is difficult for us to get the information quickly and efficiently.However,subtitles in videos often have strong semantic information,which can effectively help people understand and analyze video content,and thus quickly index and classify massive video data.The purpose of this paper is to detect subtitle text in video image quickly and accurately using deep learning technology and to achieve efficient and fast acquisition of video data content information,thus assisting relevant practitioners in the retrieval and classification of massive video data.This paper mainly studies the application of deep learning technology in video subtitle image detection,which includes two parts:subtitle text location and subtitle text recognition.Through the full investigation of the related technology of text detection,the deep learning technology is applied to the problem of video subtitle detection.The software and hardware environment of the video subtitle detection system is built.First,the corresponding video subtitle dataset is established.The character samples of the data set include 6763 common Chinese characters,26 English characters and 10 digits,etc.The diversity,balance and generalization of the samples are fully considered.Second,aiming at the specific scene of video subtitle text detection,this paper chooses Faster RCNN detection framework,uses CNN to extract image features,introduces transcendental loss function,anchor jitter and other methods to improve accuracy and recall.Finally,the whole system's serial connection and construction are completed,from video reading to caption frame interception,then to caption text line positioning,text content detection,the end-to-end process from video input to text string output is achieved.A video subtitle detection system with both speed and accuracy is designed and implemented,which can realize real-time location and recognition of video subtitle text.The accuracy and recall rate of text detection have reached 99.5%,the top-1 accuracy rate of text recognition is 97.5%,and the overall detection speed is 45 fps.