RETRACTED ARTICLE: Document image analysis: issues, comparison of methods and remaining problems

Saba, Tanzila; Sulong, Ghazali

doi:10.1007/s10462-010-9186-6

Cited by 20 publications

(3 citation statements)

References 77 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some degree of skew is unavoidable either a paper is scanned manually or mechanically (Sarfraz and Rasheed 2008;Sadri and Cheriet 2009;Saba et al 2011).…”

Section: Related Workmentioning

confidence: 99%

A Neural Approach to Cursive Handwritten Character Recognition Using Features Extracted from Binarization Technique

Choudhary

Ahlawat

Rishi

2014

Complex System Modelling and Control Through Intelligent Soft Computations

View full text Add to dashboard Cite

The feature extraction is one of the most crucial steps for an Optical Character Recognition (OCR) System. The efficiency and accuracy of the OCR System, in recognizing the off-line printed characters, mainly depends on the selection of feature extraction technique and the classification algorithm employed. This chapter focuses on the recognition of handwritten characters of Roman Script by using features which are obtained by using binarization technique. The goal of binarization is to minimize the unwanted information present in the image while protecting the useful information. Various preprocessing techniques such as thinning, foreground and background noise removal, cropping and size normalization etc. are also employed to preprocess the character images before their classification. A multi-layered feed forward neural network is proposed for classification of handwritten character images. The difference between the desired and actual output is calculated for each cycle and the weights are adjusted during error back-propagation. This process continues till the network converges to the allowable or acceptable error. This method involves the back propagation-learning rule based on the principle of gradient descent along the error surface in the negative direction. Very promising results are achieved when binarization features and the multilayer feed forward neural network classifier is used to recognize the off-line cursive handwritten characters.

show abstract

“…Some degree of skew is unavoidable either a paper is scanned manually or mechanically (Sarfraz and Rasheed 2008;Sadri and Cheriet 2009;Saba et al 2011).…”

Section: Related Workmentioning

confidence: 99%

A Neural Approach to Cursive Handwritten Character Recognition Using Features Extracted from Binarization Technique

Choudhary

Ahlawat

Rishi

2014

Complex System Modelling and Control Through Intelligent Soft Computations

View full text Add to dashboard Cite

show abstract

“…Thus, non-linear filters like median filters are used which overcomes the limitations of linear filters to an extent. As stated in [4], the median filter too causes the removal of corners and threads and may cause blurring of text, thus to overcome these limitations, a modified technique is developed, which is discussed in the following section.…”

Section: Reduction Of Noisementioning

confidence: 99%

K-Algorithm: A Modified Technique for Noise Removal in Handwritten Documents

Bansal¹,

Kumar²

2013

IJIST

View full text Add to dashboard Cite

show abstract

“…Image denoising is therefore a necessary step for finer details retrieval and other image processing [2]. It is still a challenge for researchers to restore image contaminated by noise [3].…”

Section: Introductionmentioning

confidence: 99%

Image Denoising in Frequency Domain Based on Analogical Basis Deconstruction

Liu¹,

Chao

Yuan

et al. 2013

AMM

View full text Add to dashboard Cite

In acquisition and transmission procedures, images are often contaminated by noise in spatial and frequency domain. Image denoising is usually the first step in information extraction. At present there are many frequency domain denoising methods like low pass and high pass filtering but have not yet attained a desirable level. In this paper, we proposed a new denoising method based on Analogical Basis Deconstruction (ABD) theory. It uses only uncontaminated or slightly contaminated frequency data to recover the image through Asymptotic Iterative Estimate (AIE) algorithm. The performance of new method was tested on a simulation image and compared with the traditional frequency domain methods.

show abstract

RETRACTED ARTICLE: Document image analysis: issues, comparison of methods and remaining problems

Cited by 20 publications

References 77 publications

A Neural Approach to Cursive Handwritten Character Recognition Using Features Extracted from Binarization Technique

A Neural Approach to Cursive Handwritten Character Recognition Using Features Extracted from Binarization Technique

K-Algorithm: A Modified Technique for Noise Removal in Handwritten Documents

Image Denoising in Frequency Domain Based on Analogical Basis Deconstruction

Contact Info

Product

Resources

About