Functional verification of digital TV receivers using text region extraction

Abstract

In this paper, a system for text extraction on images taken by grabbing the content from the TV screen is presented. The main goal is the image preparation for the Optical Character Recognition (OCR) to improve its accuracy. Recognized text is used for automatic generation of TV menu system structure. This menu structure is used for verification of TV set operation. The contents of the output file containing the recognized text are compared with the expected contents. This system is used as a part of Black Box Testing system in order to test and functionally verify TV set operation. The presented approach consists of several steps in image pre-processing, including character detection and segmentation. In the final step, an open-source algorithm for OCR is then run for text recognition. Finally, the improvement is tested on the range of the full image dimensions and the results are compared with those for the original image. The OCR engines are widely used in various fields of scientific research and have many uses in modern technology. The proposed method is robust for different text fonts and styles, and the results show a satisfying improvement in character recognition accuracy. © 2013 IEEE.