A comprehensive handwritten image corpus of isolated persian/arabic characters for OCR development and evaluation

Khosravi, Sara; Razzazi, Farbod; Rezaei, H.; Sadigh, Mohammad Reza

doi:10.1109/isspa.2007.4555567

Cited by 1 publication

(1 citation statement)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This database is a comprehensive 10 millions Farsi handwritten characters Database whose data and metadata was originally prepared, labeled, finalized and evaluated by Payasoft [16]. Then, a reduced set of this database was published by Tehran Polytechnic University [17].…”

Section: A Arabic/farsi Handwritten Digit Scriptsmentioning

confidence: 99%

A very high accuracy handwritten character recognition system for Farsi/Arabic digits using Convolutional Neural Networks

Ahranjany

Razzazi

Ghassemian

2010

2010 IEEE Fifth International Conference on Bio-Inspired Computing: Theories and Applications (BIC-TA)

Self Cite

View full text Add to dashboard Cite

In this paper, a new method is presented for recognizing the handwritten Farsi/Arabic digits by fusing the recognition results of a number of Convolutional Neural Networks with gradient descent training algorithm. Convolutional Neural Networks are a type of neural networks that are biologically inspired from human visual system which combines feature extraction and classification stages. This paper is concentrated on two main contributions. The first one is automatic extraction of input pattern's features by using a CNN for Farsi digits and the second one is fusing the results of boosted classifiers to compensate the recognizers' errors. The difference between competing systems is in the training set, which the frequency of samples that are "hard to recognize" were become higher in boosted classifiers. In addition, two rejection strategies were proposed and evaluated to find out "hard to recognize" samples. The experiments were conducted on extended IFH-CDB test database. The results reveal a very high accuracy classifier outperforming most of the previous systems. Theachieved result shows 99.17% in recognition rate. In addition, the result was grown up to 99.98% after rejection of ten percents of "hard to recognize" samples.

show abstract

Section: A Arabic/farsi Handwritten Digit Scriptsmentioning

confidence: 99%