&lt;title&gt;Document image restoration using binary morphological filters&lt;/title&gt;

Liang, Jisheng; Haralick, Robert M.; Phillips, Ihsin T.

doi:10.1117/12.234709

Cited by 16 publications

(9 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Text restoration step is used to repair broken and merging characters.This step is very useful for later phases of document analysis. Typical approaches to text image restoration are line following [5], Kalman filtering [6] and morphological filtering [7]. Although it was reported that MLP network can be used for filtering.…”

Section: Document Analysis and Recognitionmentioning

confidence: 99%

Research of Artificial Neural Networks Abilities in Printed Words Recognition

Bondarenko¹,

Borisov²

2010

Scientific Journal of Riga Technical University. Computer Sciences

View full text Add to dashboard Cite

Abstract-This paper provides a brief overview on document analysis and recognition area, highlighting main steps and modules that are used to build recognition systems of the mentioned type. We underline basic workflow of such system down to the problem of single character recognition problem and highlighting possibilities and ways for artificial neural networks usage. Further we are conducting a formal comparison of abilities of printed characters recognition between two well known types of second generation neural networks, namely feedforward back-propagation multilayer perceptron (MLP) and Kohonen self-organizing features map (SOM).

show abstract

Section: Document Analysis and Recognitionmentioning

confidence: 99%

Research of Artificial Neural Networks Abilities in Printed Words Recognition

Bondarenko¹,

Borisov²

2010

Scientific Journal of Riga Technical University. Computer Sciences

View full text Add to dashboard Cite

show abstract

“…OCR accuracy is improved from 6% to 38% for documents with varying quality. Liang [14] addresses the problem of document image restoration using morphological filters and achieves nearly 80% OCR accuracy for subtractive and additive noise images.…”

Section: Related Workmentioning

confidence: 99%

Text Extraction, Enhancement and OCR in Digital Video

Doermann

Kia

1999

Document Analysis Systems: Theory and Practice

View full text Add to dashboard Cite

In this paper we address the problem of text extraction, enhancement and recognition in digital video. Compared with optical character recognition (OCR) from document images, text extraction and recognition in digital video presents several new challenges. First, the text in video is often embedded in complex backgrounds, making text extraction and separation difficult. Second, image data contained in video frames is often digitized and/or subsampled at a much lower resolution than is typical for document images. As a result, most commercial OCR software can not recognize text extracted from video. We have implemented a hybrid wavelet/neural network segmenter to extract text regions and use a two stage enhancement scheme prior to recognition. First, we use Shannon interpolation to raise the image resolution, and second we postprocess the block with normal/inverse text classification and adaptive thresholding. Experimental results show that our text extraction scheme can extract both scene text and graphical text robustly and reasonable OCR results are achieved after enhancement. S . -W. Le e an d Y . N akan o ( E d s. ): DA S ' 98, LNCS 1655, p p . 363-377 , 1999. c S p r i n ge r-Ve rl ag Be rl i n He i d e l b e rg 1999

show abstract

“…Filtering approaches include noise removal using mathematical morphology 4,9 and second order filters for noise removal without blurring details 11 . Nonlinear tone mapping based on local window statistics 12 is an instance of contrast enhancement.…”

Section: Introductionmentioning

confidence: 99%

<title>Restoring high-resolution text images to improve legibility and OCR accuracy</title>

Nishida

2005

SPIE Proceedings

View full text Add to dashboard Cite

A new method for restoring high-resolution binary images is presented to improve legibility and OCR accuracy for lowresolution text images. The initially restored image is generated by simple techniques, and is then improved by integrating a variety of features obtained through image analysis. Missing strokes of characters are complemented based on topographic features. Contours of characters are then modified in terms of gradient magnitudes and curvatures along the contours. Finally, contours are beautified so that they look good to the human eye. The proposed method can deal with characters having complex structures such as Kanji, and entails relatively simple computation. Through experiments, it has been validated that the proposed method improves both OCR accuracy and legibility. In particular, smoothness and linearity along contours are significantly improved and strokes are restored correctly.

show abstract

<title>Document image restoration using binary morphological filters</title>

Cited by 16 publications

References 1 publication

Research of Artificial Neural Networks Abilities in Printed Words Recognition

Research of Artificial Neural Networks Abilities in Printed Words Recognition

Text Extraction, Enhancement and OCR in Digital Video

<title>Restoring high-resolution text images to improve legibility and OCR accuracy</title>

Contact Info

Product

Resources

About