This paper describes a new approach to detect and extract the video text more precisely and efficiently. The proposed approach combines the frame difference and the sparse representation based classification (SRC) method. The experiments demonstrated that the proposed method is effective and efficient for the both scenes, i.e. detecting and extracting the captions in a video the character in a sign.
CITATION STYLE
Sun, B., Wu, Y., Xu, F., Xiao, Y., He, J., & Chao, C. (2015). Detecting and extracting text in video via sparse representation based classification method. Lecture Notes in Electrical Engineering, 339, 351–358. https://doi.org/10.1007/978-3-662-46578-3_41
Mendeley helps you to discover research relevant for your work.