Proceedings Article10.1109/ICIP.2004.1421720
Automatic text segmentation from complex background
Qixiang Ye,Wen Gao,Qingmig Huang +2 more
- 24 Oct 2004
- Vol. 5, pp 2905-2908
51
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.
read more
Abstract: In this paper, we proposed an automatic method to segment text from complex background for recognition task. First, a rule-based sampling method is proposed to get portion of the text pixels. Then, the sampled pixels are used for training Gaussian mixture models of intensity and hue components in HSI color space. Finally, the trained GMMs together with the spatial connectivity information are used for segment all of text pixels form their background. We used the word recognition rate to evaluate the segmentation result. Experiments results show that the proposed algorithm can work fully automatically and performs much better than the traditional methods.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Text Detection and Recognition in Imagery: A Survey
Qixiang Ye,David Doermann +1 more
TL;DR: This review provides a fundamental comparison and analysis of the remaining problems in the field and summarizes the fundamental problems and enumerates factors that should be considered when addressing these problems.
876
Text detection and restoration in natural scene images
TL;DR: A new method for text detection and recognition in natural scene images is presented, based on plane-to-plane homography, and results tested from a large dataset have demonstrated that the proposed method is effective and practical.
81
Improving OCR performance with background image elimination
Mande Shen,Hansheng Lei +1 more
- 01 Aug 2015
TL;DR: A novel and cost-effective image preprocessing method that enhances the document images before OCR by utilizing the brightness and chromaticity as contrast parameters and converts color images to gray and threshold it so that background images can be removed effectively without losing the quality of text characters.
50
End-to-end scene text recognition using tree-structured models
TL;DR: A robust end-to-end scene text recognition method, which utilizes tree-structured character models and normalized pictorial structured word models, which outperforms state-of-the-art methods both for text localization and word recognition.
50
Scene Text Recognition Using Structure-Guided Character Detection and Linguistic Knowledge
TL;DR: A novel scene text-recognition method integrating structure-guided character detection and linguistic knowledge is proposed, using part-based tree structure to model each category of characters so as to detect and recognize characters simultaneously.
41
References
A Computational Approach to Edge Detection
TL;DR: There is a natural uncertainty principle between detection and localization performance, which are the two main goals, and with this principle a single operator shape is derived which is optimal at any scale.
29.9K
Color gamut transform pairs
Alvy Ray Smith
- 23 Aug 1978
TL;DR: A set of alternative models of the RGB monitor gamut based on the perceptual variables hue, saturation, and value (V) or brightness (L) are presented and algorithms for transforming between these models are derived.
Video OCR: indexing digital new libraries by recognition of superimposed captions
TL;DR: To solve two problems of character recognition for videos, low-resolution characters and extremely complex backgrounds, an interpolation filter, multi-frame integration and character extraction filters are applied and the overall recognition results are satisfactory for use in news indexing.
225
Automatic text recognition in digital videos
Rainer Lienhart,Frank Stuber +1 more
- 01 Dec 1995
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.
A new approach for video text detection
Min Cai,Jiqiang Song,Michael R. Lyu +2 more
- 10 Dec 2002
TL;DR: This paper proposes an efficient text detection approach, which is based on invariant features, such as edge strength, edge density, and horizontal distribution, and it applies edge detection and uses a low threshold to filter out definitely non-text edges.
Related Papers (5)
Wayne Niblack
- 01 Jan 1986
Simon M. Lucas,A. Panaretos,L. Sosa,A. Tang,S. Wong,R. Young +5 more
- 03 Aug 2003