A Novel Hybrid Method for Text Detection and Extraction from News Videos
Marizuana Mat Daud, Asif Abdullah, Umair Ullah Tariq, Mirza Nauman Baig, Waqar Ahmad · 2014
2 Abstract: Modern era has observed an enormous development in media information in the manifestation of audio, video and image data. Retrieval and Indexing of content-oriented video has evolved as an intriguing research zone with the colossal development in the product of advanced digital mass media. Not with standing varying media information, text showing up in videos can assist in an effective contraption for semantic abstraction, video analysis and recovery of video data. A proficient algorithm and high quality videos of news are required for accomplishing the desired task. This paper recommends a system dependent upon gray-scale edges-features for evenly arranged English ticker text localization and extraction from news videos. The framework exploits edge based localization of text regions to concentrate text based materials from videos. For low quality videos, some contrast enhancement operations are used to enhance the video frames first and then morphological operators are applied to segment out the ticker text regions in news videos. At last, these regions are cropped from the video frames and on satisfying certain geometrical constraints, the results are acknowledged to be text regions. No assumptions about the ticker color, style of text fonts, size of text and the types of ticker is made because no standard format of tickers exist in news videos of different channels and different countries have separate style of ticker texts format and color. The proposed algorithm is evaluated on a data set of CNN and BBC news videos and it displayed promising results.