Ram Sarkar

A Fuzzy Technique for Segmentation of Handwritten Bangla Word Images

A fuzzy technique for segmentation of handwritten Bangla word images is presented. It works in two steps. In first step, the black pixels constituting the Matra (i.e., the longest horizontal line joining the tops of individual characters of a Bangla word) in the target word image is identified by using a fuzzy feature. In second step, some of the black pixels on the Matra are identified as segment points (i.e., the points through which the word is to be segmented) by using three fuzzy features. On experimentation with a set of 210 samples of handwritten Bangla words, collected from different sources, the average success rate of the technique is shown to be 95.32%. Apart from certain limitations, the technique can be considered as a significant step towards the development of a full-fledged Bangla OCR system, especially for handwritten documents

Statistical comparison of classifiers for script identification from multi-script handwritten documents

Script identification for handwritten document image is an open document analysis problem especially for multilingual optical character recognition (OCR) system. To design the OCR system for multi-script document pages, it is essential to recognise different scripts before running a particular OCR system of a script. The present work reports an intelligent feature-based technique for word-level script identification in multi-script handwritten document pages. At first, the text lines and then the words are extracted from the document pages. A set of 39 distinctive features have been designed of which eight features are topological and the rest (31) are based on convex hull for each word image. For selection of a suitable classifier, performances of multiple classifiers are evaluated with the designed feature set on multiple subsets of freely available database CMATERdb1.5.1 (http://www.code.google.com/p/cmaterdb), which comprises of 150 handwritten document pages containing both Devnagari and Roman script words. Statistical significance tests on these performance measures declare MLP to be the best performing one. The overall word-level script identification accuracy with MLP classifier on the said database is observed as 99.74%.

Text line extraction from handwritten document pages using spiral run length smearing algorithm

Extraction of text lines from document images is one of the important steps in the process of an Optical Character Recognition (OCR) system. In case of handwritten document images, presence of skewed, touching or overlapping text line(s) makes this process a real challenge to the researcher. In the present work, a new text line extraction technique based on Spiral Run Length Smearing Algorithm (SRLSA) is reported. Firstly, digitized document image is partitioned into a number of vertical fragments of equal width. Then all the text line segments present in these fragments are identified by applying SRLSA. Finally, the neighboring text line segments are analyzed and merged (if necessary) to place them inside the same text line boundary in which they actually belong. For experimental purpose, the technique is tested on CMATERdb1.1.1 and CMATERdb1.2.1 databases. The present technique extracts 87.09% and 89.35% text lines successfully from the said databases respectively.

Statistical validation of multiple classifiers over multiple datasets in the field of pattern recognition

Classification is a machine learning technique which is used to categorise the different input patterns into different classes. To select the best classifier for a given dataset is one of the critical issues in pattern classification. Using cross-validation approach, it is possible to apply candidate algorithms on a given dataset and best classifier is selected by considering various evaluation measures of classification. But computational cost associated with this approach is trivial in nature. There are a lot of tests described in the literature but they are specifically used on different and non-related datasets. But, in pattern recognition domain the datasets are taken from the same testing samples and hence are related in nature. In this paper, we propose the use of two non-parametric tests, namely Mann-Whitney U test for comparison of two classifiers and Kruskal-Wallis H test with the corresponding post-hoc tests for comparison of multiple classifiers on multiple datasets. The tests have been fruitfully applied on the datasets of handwritten digit recognition problem taken from UCI Machine Learning Database Repository (http://www.ics.uci.edu/~mlearn). The results show that both the tests provide a better solution than previously proposed tests.

A Font Invariant Character Segmentation Technique for Printed Bangla Word Images

A solution for segmentation of Bangla word images, printed in different fonts with varying styles and sizes, into constituent characters is reported here. Firstly, three horizontally non-intersecting zones viz., Upper, Middle and Lower Zones of a given word are identified. Then, estimation of the probable black pixels, which constitute common Matra of the word, a prominent feature in Bangla script, is done. Some of the black pixels on the Matra region are selected as potential segmentation points to segment the word vertically into their constituent characters. Each of these segmented components is then categorized into any of the six possible component types (viz. upper/middle/lower zone component/ middle and lower zone component/ broken character component/noise component). Middle and lower zone components are separated horizontally. The methodology is tested on 1600 word images of different fonts with varying styles and sizes and average success rate achieved is 96.85%.

Word Segmentation from Unconstrained Handwritten Bangla Document Images using Distance Transform

Segmentation of handwritten document images into text lines and words is one of the most significant and challenging tasks in the development of a complete Optical Character Recognition (OCR) system. This paper addresses the automatic segmentation of text words directly from unconstrained Bangla handwritten document images. The popular Distance transform (DT) algorithm is applied for locating the outer boundary of the word images. This technique is free from generating the over-segmented words. A simple post-processing procedure is applied to isolate the under-segmented word images, if any. The proposed technique is tested on 50 random images taken from CMATERdb1.1.1 database. Satisfactory result is achieved with a segmentation accuracy of 91.88% which confirms the robustness of the proposed methodology.

Handwritten Script Identification from Text Lines

In a multilingual country like India where 12 different official scripts are in use, automatic identification of handwritten script facilitates many important applications such as automatic transcription of multilingual documents, searching for documents on the web/digital archives containing a particular script and for the selection of script specific Optical Character Recognition (OCR) system in a multilingual environment. In this paper, we propose a robust method towards identifying scripts from the handwritten documents at text line-level. The recognition is based upon features extracted using Chain Code Histogram (CCH) and Discrete Fourier Transform (DFT). The proposed method is experimented on 800 handwritten text lines written in seven Indic scripts namely, Gujarati, Kannada, Malayalam, Oriya, Tamil, Telugu, Urdu along with Roman script and yielded an average identification rate of 95.14% using Support Vector Machine (SVM) classifier.

A New Approach for Texture based Script Identification At Block Level using Quad- Tree Decomposition

A considerable amount of success has been achieved in developing monolingual OCR systems for Indic scripts. But in a country like India, where multi-script scenario is prevalent, identifying scripts beforehand becomes obligatory. In this paper, we present the significance of Gabor wavelets filters in extracting directional energy and entropy distributions for 11 official handwritten scripts namely, Bangla, Devanagari, Gujarati, Gurumukhi, Kannada, Malayalam, Oriya, Tamil, Telugu, Urdu and Roman. The experimentation is conducted at block level based on a quad-tree decomposition approach and evaluated using six different well-known classifiers. Finally, the best identification accuracy of 96.86% has been achieved by Multi Layer Perceptron (MLP) classifier for 3-fold cross validation at level-2 decomposition. The results serve to establish the efficacy of the present approach to the classification of handwritten Indic scripts