Recognition of multi-type and multi-oriented text in videos / Sangheeta Roy

Sangheeta , Roy (2018) Recognition of multi-type and multi-oriented text in videos / Sangheeta Roy. PhD thesis, University of Malaya.

	PDF (The Candidate's Agreement) Restricted to Repository staff only Download (128Kb)
Preview	PDF (Thesis PhD) Download (5Mb) | Preview

Abstract

Text inscribed in video plays an important role to understand the semantic essence of the content in several real-time application, such as video events indexing and retrieval, license plate recognition, automatic navigation, and surveillance applications. Since video suffers from multi-text type, multi-oriented text, low resolution, complex background, thus achieving accurate recognition results is challenging and interesting. In general text appearance and background in video differs according to application and problems. Therefore, in this thesis, a new method has been proposed based on texts and its background to classify the video type, which results in the video of particular text type. To enhance the video images from the effect of Laplacian operation, fractional Poisson model has been introduced for removing noise introduced by Laplacian operation in the video. A multimodal approach is explored for detecting words in complex video images, such as sports, Marathon video images, etc. which can cope with the causes of background and foreground variations. Then detected words are used for keyword spotting in the video to retrieve the video frames efficiently. Since keyword spotting does not involve semantic information to retrieve the video events, a new classification algorithm has been proposed based on tampered and context features to classify the caption and scene text types which facilitates recognition to achieve good recognition rate. To recognize the text in video images, Bayesian classifier-based method has been investigated for binarization to use available OCR. However, the primary focus of this approach limits to horizontal English texts. Therefore, Hidden Markov Model-based recognition method which works without binarization has been proposed for recognizing the text of multiple scripts. The proposed methods are evaluated over standard datasets and our own datasets using standard evaluation metrics. Furthermore, the proposed methods are compared with existing recent methods to show that proposed methods outperform the existing methods in terms of quality and quantity measures.

Actions (For repository staff only : Login required)