A Complete Workflow for Development of Bangla OCR

Omee, Farjana Yeasmin; Himel, Shiam Shabbir; Bikas, Abu Naser

doi:10.5120/2543-3483

Cited by 19 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This review concludes that many promising methodologies were developed for OCR and HOCR in last few decades for Indian scripts like English (cursive) [26], Arabic [27], Gurumukhi [32], Persian [35], Devnagari [36], Tamil [44], Telugu [45], Bengali [46], and Kannada [47], Urdu [48], Gujarati [49] and Malayalam [50,51].…”

Section: Post-processingmentioning

confidence: 99%

Review on Recent Advances in Automatic Handwritten MODI Script Recognition

Sadanand¹,

Borde²,

Ramesh³

et al. 2015

IJCA

View full text Add to dashboard Cite

Many HOCR systems was developed for different foreign language and efforts on Indian script still verdant. Due to the varying writing style of each individual HOCR becomes a critical challenge since last few decades. India was known to world for its unity in diversity. The geographical and cultural vastness of the country various spoken languages and writing scripts were invented and utilized for daily communication. Courageous endeavors was made towards HOCR for various Indian scripts. The development of HOCR system was considered an active area of research due to the complexity and structure of Indian scripts. MODI Script was an ancient script of India as compared with other Indian scripts. Large number of historical documents exists and they need to be preserved and explored therefore special attention must be given to MODI script. This research paper is an attempt towards an investigation of recent advances in Handwritten Optical Character Recognition system for MODI script.

show abstract

Section: Post-processingmentioning

confidence: 99%

Review on Recent Advances in Automatic Handwritten MODI Script Recognition

Sadanand¹,

Borde²,

Ramesh³

et al. 2015

IJCA

View full text Add to dashboard Cite

show abstract

“…We have trained Tesseract 3.0 for Bengali character. After training Tesseract 3.0, then we use it a bangle open source OCR named SHABDAYON [28] which is developed in C++ language. As we developed our system using java so we had to linkage java code and C++ code.…”

Section: Number Plate Recognitionmentioning

confidence: 99%

An Automatic Number Plate Recognition of Bangladeshi Vehicles

Amin¹,

Mohammad²,

Bikas³

2014

IJCA

View full text Add to dashboard Cite

Now-a-day, the importance of automatic traffic monitoring has drawn the attention to the intelligent transport systems. A number plate is the unique identification of a vehicle. Automatic Number Plate Recognition (ANPR) is designed to locate and recognize the number plate of a moving vehicle automatically. For Bangladeshi Vehicles there are no fixed rules for number plates like other countries. Because of the variety of conditions and patterns, the recognition process of number plates for Bangladeshi vehicles is so difficult. We develop a ANPR system which is divided into three part such as number plate Localization, Extraction and Recognition. After successfully complete localization and extraction of number plate we send that portion to a Bangla OCR to fetch the text of the number plate for further processing. In this paper we present a complete ANPR system for Bangladesh Vehicles using standard algorithms with some customization and with our own algorithm for Number Plate extraction which can detect Number Plate region and successfully extract detected region and then able to recognize that number plate text.

show abstract

“…Hence, a mechanism is inevitably needed which helps to bring all sorts of information on the digital platform. This proves the fact that Document Image binarization has an important role to play as far as document-digitization is considered [4][5][6]. This paper is basically written with an aim to provide a detailed study about document binarization and image segmentation, mainly carried out on Tamil documents.…”

Section: Introductionmentioning

confidence: 99%

Combined Method of Level set with impact on Pre-processing for binarization of document images in Tamil Script

Ashok¹,

Dhivya²,

Jansirani³

et al. 2012

IJCA

View full text Add to dashboard Cite

Binarization and Segmentation are considered to be the vital tasks in Optical Character Recognition (OCR) for document digitization. This paper discusses the applications of powerful Level set methodologies on these important tasks associated with OCR. Results acquired for these essential procedures in turn govern the accuracy of the OCR system. Conventionally Otsu method and Histogram profiling methods were used for binarization and segmentation purpose [1]. In this paper, we try to replace these different methods by a single procedure based on Level Set methodology, where segmentation and binarization for any document could be efficiently done in a single step. The main advantage of this method is that it does not require separate paragraph segmentation, line segmentation and character segmentation. We have also compared the working and performance of two algorithms based on Active Contour or Level Set Model: Selective Binary and Gaussian Filtering Regularized Level Set (SBGFRLS) by Zhang [2] and Split Bresson"s Chan Vese Level Set methods by Bresson [3] in the case of real data and test data embedded with noise taken from Tamil script.

show abstract

A Complete Workflow for Development of Bangla OCR

Cited by 19 publications

References 15 publications

Review on Recent Advances in Automatic Handwritten MODI Script Recognition

Review on Recent Advances in Automatic Handwritten MODI Script Recognition

An Automatic Number Plate Recognition of Bangladeshi Vehicles

Combined Method of Level set with impact on Pre-processing for binarization of document images in Tamil Script

Contact Info

Product

Resources

About