Text segmentation and recognition in complex background based on Markov random field
Datong Chen,J.-M. Olobez,Hervé Bourlard +2 more
- Vol. 4, pp 40227
Reads0
Chats0
TLDR
By varying the number of gaussians, multiple hypotheses are provided to an OCR system and the final result is selected from the set of outputs, leading to an improvement of the system's performances.Abstract:
In this paper we propose a method to segment and recognize text embedded in video and images. We modelize the gray level distribution in the text images as mixture of gaussians, and then assign each pixel to one of the gaussian layer. The assignment is based on prior of the contextual information, which is modeled by a Markov random field (MRF) with online estimated coefficients. Each layer is then processed through a connected component analysis module and forwarded to the OCR system as one segmentation hypothesis. By varying the number of gaussians, multiple hypotheses are provided to an OCR system and the final result is selected from the set of outputs, leading to an improvement of the system's performances.read more
Citations
More filters
Journal ArticleDOI
Text information extraction in images and video: a survey
TL;DR: A large number of techniques to address the problem of text information extraction are classified and reviewed, benchmark data and performance evaluation are discussed, and promising directions for future research are pointed out.
Proceedings ArticleDOI
Scene Text Recognition using Higher Order Language Priors
TL;DR: A framework is presented that uses a higher order prior computed from an English dictionary to recognize a word, which may or may not be a part of the dictionary, and achieves significant improvement in word recognition accuracies without using a restricted word list.
Journal ArticleDOI
Fast and robust text detection in images and video frames
TL;DR: A novel coarse-to-fine algorithm that is able to locate text lines even under complex background is proposed and Experimental results show that this approach can fast and robustly detect text lines under various conditions.
Journal ArticleDOI
A localization/verification scheme for finding text in images and video frames based on contrast independent features and machine learning methods
TL;DR: This scheme provides fast text detection in images and videos with a low computation cost, comparing with traditional methods.
Proceedings ArticleDOI
Automatic text segmentation from complex background
Qixiang Ye,Wen Gao,Qingmig Huang +2 more
TL;DR: An automatic method to segment text from complex background for recognition task by using a rule-based sampling method and trained GMMs together with the spatial connectivity information.
References
More filters
Journal ArticleDOI
Maximum likelihood from incomplete data via the EM algorithm
Journal ArticleDOI
Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images
Stuart Geman,Donald Geman +1 more
TL;DR: The analogy between images and statistical mechanics systems is made and the analogous operation under the posterior distribution yields the maximum a posteriori (MAP) estimate of the image given the degraded observations, creating a highly parallel ``relaxation'' algorithm for MAP estimation.
Proceedings ArticleDOI
Video OCR for digital news archive
TL;DR: This paper applies an interpolation filter, multi-frame integration and a combination of four filters to solve the problems of character recognition for videos: low resolution characters and extremely complex backgrounds.
Proceedings ArticleDOI
Finding text in images
TL;DR: A four-step system which automaticnlly detects and extracts text in images is proposed and works well on imayes (with or without structured layouts) from a wide range of sources, including digitized video frames, photographs, and personal checks.
Proceedings ArticleDOI
Automatic text recognition in digital videos
Rainer Lienhart,Frank Stuber +1 more
TL;DR: Algorithms for automatic character segmentation in motion pictures which extract automatically and reliably the text in pre-title sequences, credit titles, and closing sequences with title and credits are developed.