Abstract
With the development of deep learning, the detection and recognition of text in natural images become much significant not only in academic field, but in daily life application. This technology, consists of end-to-end optical Chinese character recognition, can be easily employed in the transition from images to text. There are two main sections involved in this technology -- the detection and the recognition. For the detection, the state-of-the-art method is Region-CNN (R-CNN) and Region Proposal Network (RPN); and for the recognition, the state-of-the-art method is CNN. In this article, we employ Connectionist Text Proposal Network (CPTN) to detect sequential text lines in natural images, and incorporate Connectionist Temporal Classification (CTC) into DenseNet to recognize the text and transit it to Chinese characters.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
