Abstract
This paper proposes a novel text localization method in natural images based on the connected components (CC) approach. First, CC are isolated by convolving a multi-scale pyramid with a specifically designed linear spatial filter followed by hysteresis thresholding. Next, non-textual CC are pruned employing a local classifier consisting of a cascade of multilayer perceptron (MLP) fed with increasingly extended feature vectors. The stroke width feature is estimated in linear time complexity by computing the maximal inscribed squares in the CC. Candidate CC and their neighbors are then checked using a more global MLP classifier that takes into account the target CC and their vicinity. Finally, text sequences are extracted in all pyramid levels and fused using dynamic programming. The main contribution of the proposed method is its execution speed, being capable of processing 1080p HD video at nearly 30 frames per second on a standard laptop. In addition, it delivers competitive results interms of precision and recall on the ICDAR 2013 Robust Reading dataset.
Sign-in/Register to access full text options 
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.
