A System for Handwritten Script Identification From Indian Document

Obaidullah, Sk Md; Das, Supratik Kundu

doi:10.13176/11.485

Cited by 29 publications

(14 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…MLP consists of three layers with the number of neurons in each layer represented as a directed graph [3]. In our experiment, we choose the configuration of the MLP as 148-hl-8 (i.e.…”

Section: Mlpmentioning

confidence: 99%

“…Nowadays, OCR for different scripts is available throughout the world and the work is progressing very rapidly. But there is a problem for OCR development in a country like India, where 23 different languages (including English) are present and 11 different scripts (including Roman) are used to write them ( [2]; [3]), making India as a multi-lingual/multi-script country. In our day to day life we come across various documents which are multi-script in nature such as postal documents and pre-printed application form Fig.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automatic Line-Level Script Identification From Handwritten Document Images - A Region-Wise Classification Framework for Indian Subcontinent

Obaidullah

Halder

Santosh

et al. 2018

MJCS

Self Cite

View full text Add to dashboard Cite

Script identification is a well-studied problem for automatic processing of document images. Several attempts have been made so far, but it is still far ahead from the complete solution. In this paper, an automatic approach for line-level handwritten script identification (HSI), considering eight official Indic scripts namely: Bangla, Devanagari, Kannada, Malayalam, Oriya, Roman, Telugu, and Urdu is proposed. We consider a 148-dimensional feature vector using: image component fractal dimension, structural and visual appearance, directional stroke, interpolation and Gabor energy based texture features. For classification, we divide the whole script dataset based on different regions of India, to study a region-wise classification performance. Experimentation was carried out using the state-of-the-art classifiers: multilayer perceptron (MLP), support vector machine (SVM), random forest (RF), and fuzzy unordered rule induction algorithm (FURIA). Among all, we found that MLP as the best performer in terms of average accuracy of 98.2%, 99.5%, 99.1%, 99.5%, 99.9%, 98%, 98.9% for eight-script, bi-script, eastern, north, south Indian script groups, scripts with 'matra' vs without 'matra', and dravidian vs. non-dravidian groups respectively.

show abstract

“…MLP consists of three layers with the number of neurons in each layer represented as a directed graph [3]. In our experiment, we choose the configuration of the MLP as 148-hl-8 (i.e.…”

Section: Mlpmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Automatic Line-Level Script Identification From Handwritten Document Images - A Region-Wise Classification Framework for Indian Subcontinent

Obaidullah

Halder

Santosh

et al. 2018

MJCS

Self Cite

View full text Add to dashboard Cite

show abstract

“…Finally, using component labeling, each component is selected and mapped them in the original gray scale image to get respective zones of the original image. Final binary image (0, 1) is obtained using histogram based global binarization algorithm on these regions of the original image [3,8,12,31].…”

Section: A Preprocessingmentioning

confidence: 99%

“…But the prerequisite for those algorithms are knowledge of the particular script by which the language is written. It is worth to mention here, in India 23 official languages are present (including English) [3] and 13 scripts are there to write those languages. Apart from this Roman script is very popular in India which is used to write English and Santali languages.…”

Section: Introductionmentioning

confidence: 99%

Convolution Based Technique for Indic Script Identification from Handwritten Document Images

Obaidullah¹,

Das²

2015

IJIGSP

Self Cite

View full text Add to dashboard Cite

Abstract-Determination of script type of document image is a complex real life problem for a multi-script country like India, where 23 official languages (including English) are present and 13 different scripts are used to write them. Including English and Roman those count become 23 and 13 respectively. The problem becomes more challenging when handwritten documents are considered. In this paper an approach for identifying the script type of handwritten document images written by any one of the Bangla, Devnagari, Roman and Urdu script is proposed. Two convolution based techniques, namely Gabor filter and Morphological reconstruction are combined and a feature vector of 20 dimensions is constructed. Due to unavailability of a standard data set, a corpus of 157 document images with an almost equal ratio of four types of script is prepared. During classification the dataset is divided into 2:1 ratio. An average identification accuracy rate of 94.4% is obtained on the test set. The average Bi-script and Tri-script identification accuracy rate was found to be 98.2% and 97.5% respectively. Statistical performance analysis is done using different well known classifiers.

show abstract

“…Using component labeling, they select each component to map in the original gray image to get respective zones of the original image. Final binarized image is obtained using histogram based global binarization algorithm on these regions of the original image[1]. Considerably good accuracy of 98.5% on more than eleven thousand test words was achieved[9].…”

mentioning

confidence: 99%

Study of Different Features and Classification Techniques for Recognition of Handwritten Devanagari Text

Vijay¹,

Kharat²,

Gumaste³

2018

IJET

View full text Add to dashboard Cite

Devanagari script is most popular and an older script in India. Millions of people all over the globe are using Devanagri script for various purposes such as communication, understanding the history, record keeping, research, etc. Recognition of handwritten Devanagari word is one of the popular area of research from decades because of its wide scope of applications. Different features and techniques of classification are the most important steps in the process of recognizing Devanagari handwritten word, are described in this paper.

show abstract

A System for Handwritten Script Identification From Indian Document

Cited by 29 publications

References 0 publications

Automatic Line-Level Script Identification From Handwritten Document Images - A Region-Wise Classification Framework for Indian Subcontinent

Automatic Line-Level Script Identification From Handwritten Document Images - A Region-Wise Classification Framework for Indian Subcontinent

Convolution Based Technique for Indic Script Identification from Handwritten Document Images

Study of Different Features and Classification Techniques for Recognition of Handwritten Devanagari Text

Contact Info

Product

Resources

About