1999
DOI: 10.1109/34.809116
|View full text |Cite
|
Sign up to set email alerts
|

Textfinder: an automatic system to detect and recognize text in images

Abstract: ÐA robust system is proposed to automatically detect and extract text in images from different sources, including video, newspapers, advertisements, stock certificates, photographs, and checks. Text is first detected using multiscale texture segmentation and spatial cohesion constraints, then cleaned up and extracted using a histogram-based binarization algorithm. An automatic performance evaluation scheme is also proposed.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

1
150
0
4

Year Published

2003
2003
2019
2019

Publication Types

Select...
4
3
2

Relationship

0
9

Authors

Journals

citations
Cited by 330 publications
(155 citation statements)
references
References 19 publications
1
150
0
4
Order By: Relevance
“…Early research has used texture segmentation with heuristics to detect text in non-document settings [19]. Other work has applied machine learning as in [20] where a boosted classifier is trained to detect text in street images.…”
Section: Related Workmentioning
confidence: 99%
“…Early research has used texture segmentation with heuristics to detect text in non-document settings [19]. Other work has applied machine learning as in [20] where a boosted classifier is trained to detect text in street images.…”
Section: Related Workmentioning
confidence: 99%
“…Binarization: Once the bounding box of each word is obtained, each region in the bounding box is binarized using a simple but effective histogram based binarization method proposed by [5]. This word region is binarized using the computed threshold to yield a binary image of the region thus highlighting the text.…”
Section: Bottom Up Analysismentioning
confidence: 99%
“…The present approach yields good grouping of text components into words. The isolated word regions are binarized by the technique proposed by Wu et al [5].…”
Section: Introductionmentioning
confidence: 99%
“…A robust system is proposed by V. Wu [11] to automatically detect and extract text in images from different sources, including video, newspapers, advertisements, stock certificates, photographs, and checks. X. Gao et al [12] present algorithms for detection, extraction, binarization and recognition of Chinese video captions.…”
Section: Introductionmentioning
confidence: 99%