Segmentation of touching and fused Devanagari characters

Bansal, Veena; Sinha, R.M.K.

doi:10.1016/s0031-3203(01)00081-4

Cited by 105 publications

(48 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(a) Horizontal Projection: For a given binary image of sizeL×M, whereLis the heightand M is the width of the image, the horizontal projection is defined by Bansal [12] as:…”

Section: Segmentation Of Word Into Unique Charactermentioning

confidence: 99%

Line-wise Script Segmentation for Indian Language Documents

Shukla¹,

Banka²

2014

IJCA

View full text Add to dashboard Cite

“…(a) Horizontal Projection: For a given binary image of sizeL×M, whereLis the heightand M is the width of the image, the horizontal projection is defined by Bansal [12] as:…”

Section: Segmentation Of Word Into Unique Charactermentioning

confidence: 99%

Line-wise Script Segmentation for Indian Language Documents

Shukla¹,

Banka²

2014

IJCA

View full text Add to dashboard Cite

“…A method to segment the touching character in upper zone of Gurumukhi script has also been suggested [23,24]. A technique for segmentation of the conjuctiction (one kind of touching patterns) in Devnagari script using the structure properties of the script has also been implemented [25]. Apart from these, other relevant works have been enlisted in Table 1.…”

Section: Literature Reviewmentioning

confidence: 99%

Automatic Recognition of Handwritten Bengali Broken Characters (BBC): Simulating Human Pattern Matching

Nayak¹,

Nayak²,

Yetirajam³

et al. 2012

IJCA

View full text Add to dashboard Cite

This paper presents an automatic detection of handwritten Bengali Broken Characters (BBC) using a feed forward neural network (FFNN). It simulates the Human Visual System (HVS) the way human eye matches the patterns of the broken characters to a meaningful character and identifies it. Here the challenge is to detect and retrieve handwritten character which has been distorted up to 90%. The database consists of fifty bangle characters, each with twenty samples. Each character is presented as an image, which has been preprocessed, segmented and the features are then extracted. A new method has been proposed in this paper. It uses FFNN to calculate the mismatch for the recognition of a character, where it is observed that the distorted characters show very low mismatch with the original characters. For example, characters up to 70% distortions are found to be retrieved effectively.

show abstract

“…The conjuncts are separated using connected components approach. Bansal, V [6] Proposes an algorithm for the structural properties of the script. The width and height of each character is calculated and used for identifying the touching characters.…”

Section: Techniques For Segmenting Touching Charactersmentioning

confidence: 99%

“…Structural properties [6] Vertical projection, horizontal projection, divide the character into 3 parts [3] NA…”

Section: Document Related Noisementioning

confidence: 99%

A Language Independent Characterization of Document Image Noise in Historical Scripts

Sandhya¹,

Krishnan²,

Babu³

2012

IJCA

View full text Add to dashboard Cite

Digitization of historical documents helps preserve these documents. As these documents have existed for a long time, various types of noise creep in. In our paper we have analyzed the different types of noise that occur in printed and handwritten historical documents mainly based on Kannada (Kannada is a language used in Karnataka, a southern state in India) documents and created a taxonomy for the same. We have also characterized each noise type based on factors such as their source, their effect on characters and the associated challenges in character recognition. We have also catalogued the different noise detection, removal and restoration techniques that are reported in the literature for each of the prominent noise types, and identified areas relating to noise detection, removal for further research focus.

show abstract

Segmentation of touching and fused Devanagari characters

Cited by 105 publications

References 12 publications

Line-wise Script Segmentation for Indian Language Documents

Line-wise Script Segmentation for Indian Language Documents

Automatic Recognition of Handwritten Bengali Broken Characters (BBC): Simulating Human Pattern Matching

A Language Independent Characterization of Document Image Noise in Historical Scripts

Contact Info

Product

Resources

About