Abstract
This article proposes a scheme for automatic text extraction from scene images. The work is composed of two steps. In the first step, we apply a model based color segmentation procedure in the LCH color space. This step produces certain homogenous connected components (CCs) from the image. In the next step, these CCs are examined in order to identify possible text components. A number of features that distinguish between text and non-text components, are defined. Further, during learning, these features are considered independently and approximated using parametric distribution families. Finally, the joint distribution of the features are constructed using a multivariate Gaussian copula. Consequently, we obtain two copula based class distributions for the two classes (text and non-text). Afterwards, during testing, a CC belongs to the class that produces the highest class distribution probability. Our experiments are on the database of ICDAR 2003 Robust Reading Competition. The experimental results are satisfactory.
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.
