oalib
Search Results: 1 - 10 of 100 matches for " "
All listed articles are free for downloading (OA Articles)
Page 1 /100
Display every page Item
Segmentation and Recognition of Arabic Printed Script
Fakir Mohamed Fakir
IAES International Journal of Artificial Intelligence (IJ-AI) , 2013, DOI: 10.11591/ij-ai.v2i1.1236
Abstract: In this work we present a method for the recognition of Arabic printed script. The major problem of the automatic reading of cursive writing is a segmentation of script to isolate characters. The recognition process consists of four phases: Preprocessing, segmentation, feature extraction and the recognition. In the preprocessing, the image is scanned and smoothed. The correction of skew lines is done by using Hough transform . In the second phase, the text is segmented into lines, words or parts of words and each word into characters based on the principle of projection of the histogram. Features such as: density, profile, Hu moments and histogram are used to classifier the characters based on the Neural network.
Designing a Segment Display Model for Bengali and English Numerical Digits and Characters
Mohammad Shamsul Arefin
Asian Journal of Information Technology , 2012,
Abstract: Seven-segment display is well known for displaying the English digits from 0 to 9. A 16-segment display is used to display the English characters. Lots of works are going on to display the Bengali numerical digits and characters properly. These works have the limitations that they cannot provide the facility of displaying both numerical digits and characters of Bengali and English. In this paper a 34-segment display model has been designed which is able to display Bengali and English numerical digits, vowels and consonants. The required logic circuit for each segment was also designed to activate the digits and characters.
Classification and Recognition of Printed Hindi Characters Using Artificial Neural Networks
B.Indira,M.Shalini,M.V. Ramana Murthy,Mahaboob Sharief Shaik
International Journal of Image, Graphics and Signal Processing , 2012,
Abstract: Character Recognition is one of the important tasks in Pattern Recognition. The complexity of the character recognition problem depends on the character set to be recognized. Neural Network is one of the most widely used and popular techniques for character recognition problem. This paper discusses the classification and recognition of printed Hindi Vowels and Consonants using Artificial Neural Networks. The vowels and consonants in Hindi characters can be divided in to sub groups based on certain significant characteristics. For each group, a separate network is designed and trained to recognize the characters which belong to that group. When a test character is given, appropriate neural network is invoked to recognize the character in that group, based on the features in that character. The accuracy of the network is analyzed by giving various test patterns to the system.
A New Approach for Displaying All Bengali Characters
Samiran Mahmud,Ahmed Shamsul Arefin,Md. Ibrahim Khan
Asian Journal of Information Technology , 2012,
Abstract: Seven segments display for 0-9 numerals are used in all sorts of electronic equipments. In this study an 31 segments display system has been proposed for bangle characters, both Digits and alphabets. First a grid structure consisting of 31 segments has been discovered so that all the bangle digits can be characterized by this segments. As there can be at most 10 digits(0-9) to be displayed,4 bit inputs are used to represent each digit. Then after analyzing which are segments to be activated to be activated for which digit, appropriate logic circuit have been derived in order to display each bangla digit
A Learning Vector Quantization Based Recognition Technique for Arabic Characters
Amer Al- Nassiri
Asian Journal of Information Technology , 2012,
Abstract: Artificial Neural Networks (ANN `s) have been successfully applied to optical character recognition (OCR) yielding excellent results. This paper describes improvements to a system that recognize Arabic character in a low and high resolution binary document images. A classical conventional algorithm that uses chain coding for the segmentation of words, while an Learning Vector Quantization (LVQ) network is used to identify the segmented Arabic characters. Performance advances reflected in the current system largely result from the introduction of ensembles Freeman Arabic Classification Tree (FACT) (Al-Nasssiri, 2001), as the base for LVQ recognizer. By using features produced by chain coding algorithm, FACT, and LVQ (as a classifier), we have obtained high recognition rate on printed Arabic character. Application of LVQ demonstrates the arbitrary of the method to significantly reduce the computational lost of the classification system and improves the recognition rate. On characters extracted from more than 40 test images (pages) scanned with various kinds of scanners with 300 and 600 dpi scanning resolution, in addition to various degree of noise, the current system attains a character recognition rate within 88- 92%.
Design of a 19 Segment Display for Bengali Vowels, Bengali andEnglish Digits
A. K. M. Najmul Islam,S. M. Milky Mahmud,Nazib Shahriar
Asian Journal of Information Technology , 2012,
Abstract: Seven-segment display is well-known for displaying the English digits form 0 to 9. A 16 segment display is used to display the English characters. Already a 17 segment display for displaying the vowels of Bengali characters has been designed. In this Study we have designed a 19 segment display for displaying the Bengali vowels and Bengali & English digits. First of all we have arranged the segments in such a way so that we can display all the Bengali vowels and Bengali & English digits with that arrangement. From the review it appears that it is the first proposed combined display model for Bengali vowels and Bengali & English digits.
Printed Arabic Characters Classification using A Statistical Approach  [cached]
Ihab Zaqout
International Journal of Computers & Technology , 2012,
Abstract: In this paper, we propose simple classifiers for printed Arabic characters based on statistical analysis. 109 printed Arabic character images are created for each one of transparent, simplified and traditional Arabic fonts. Images are preprocessed by the binarization and followed by sequence of morphological operations. A non-linear filter is applied on the thinned ridge map to extract termination and bifurcation features. The thinned ridge map vectors (TRMVs) are created using a freeman chain code template. The spatial distribution and statistical properties of the extracted features are calculated.
Segmented Display System for Bengali Consonants
Salahuddin Mohammad Masum,Sarwar Morshedul Haque,Swapon Chandra Dash,Kazi Faisal Kabir
Asian Journal of Information Technology , 2012,
Abstract: Well–established segmented display system for English digits, English characters and some recent research works on designing segmented display system for Bengali digits and vowels have proven extreme significance of a standard segmented display system for Bengali consonants. In this study, we have presented a 44–segment display system for Bengali consonants to set a standard in the display system of Bengali alphabet and to save significant amount of time, effort, and storage space. To illuminate all the Bengali consonants, we have introduced 6–bit inputs to represent all the Bengali consonants, analyzed all the 44 segments against each and every consonant, and designed the suitable circuits for each of the 44 segments.
TOPOGRAPHIC FEATURE EXTRACTION FOR BENGALI AND HINDI CHARACTER IMAGES
Soumen Bag,Gaurav Harit
Signal & Image Processing , 2011,
Abstract: Feature selection and extraction plays an important role in different classification based problems such as face recognition, signature verification, optical character recognition (OCR) etc. The performance of OCR highly depends on the proper selection and extraction of feature set. In this paper, we present novel features based on the topography of a character as visible from different viewing directions on a 2D plane. By topography of a character we mean the structural features of the strokes and their spatial relations. In this work we develop topographic features of strokes visible with respect to views from different directions (e.g. North, South, East, and West). We consider three types of topographic features: closed region, convexity of strokes, and straight line strokes. These features are represented as a shapebased graph which acts as an invariant feature set for discriminating very similar type characters efficiently. We have tested the proposed method on printed and handwritten Bengali and Hindi character images. Initial results demonstrate the efficacy of our approach.
Topographic Feature Extraction for Bengali and Hindi Character Images  [PDF]
Soumen Bag,Gaurav Harit
Computer Science , 2011, DOI: 10.5121/sipij.2011.2215
Abstract: Feature selection and extraction plays an important role in different classification based problems such as face recognition, signature verification, optical character recognition (OCR) etc. The performance of OCR highly depends on the proper selection and extraction of feature set. In this paper, we present novel features based on the topography of a character as visible from different viewing directions on a 2D plane. By topography of a character we mean the structural features of the strokes and their spatial relations. In this work we develop topographic features of strokes visible with respect to views from different directions (e.g. North, South, East, and West). We consider three types of topographic features: closed region, convexity of strokes, and straight line strokes. These features are represented as a shape-based graph which acts as an invariant feature set for discriminating very similar type characters efficiently. We have tested the proposed method on printed and handwritten Bengali and Hindi character images. Initial results demonstrate the efficacy of our approach.
Page 1 /100
Display every page Item


Home
Copyright © 2008-2017 Open Access Library. All rights reserved.