Dergiler / Engineering Sciences / 2019 / Cilt: 14 Sayı: 2

Handwritten Amharic Character Recognition System Using Convolutional Neural Networks

HANDWRITTEN AMHARIC CHARACTER RECOGNITION SYSTEM USING CONVOLUTIONAL NEURAL NETWORKS

Sayfa
71–87
Yayın Tarihi
2019-04-20
DOI
—
🏛️Bu makalenin bibliyografik verileri ve tam metin bağlantısı DergiPark üzerinden sağlanmıştır.
DergiPark Kaydı ↗
✨

Yapay Zeka Hızlı Bakış & Çıkarımlar

AI Insight
⚡ TL;DR(1 Cümlede Hızlı Çıkarım)

Our proposed CNN model gives an accuracy of 91.83% on training data and 90.47% on validation data.

📌 3 Maddede Bu Makale

🎯
Amaç & Hipotez:Amharic language is an official language of the federal government of the Federal Democratic Republic of Ethiopia.
📊
Temel Bulgular & Veri:In order to recognize handwritten Amharic character a novel method based on deep neural networks is used which has recently shown exceptional performance in various pattern recognition and machine learning applications, but has not been endeavoured for Ethiopic script.
💡
Sonuç & Katkı:Our proposed CNN model gives an accuracy of 91.83% on training data and 90.47% on validation data.
🔬Tür:Modelleme & Sayısal Simülasyon
📍Kapsam:Genişletilmiş Akademik Örneklem
⚙️Değişkenler:Amharic · Handwritten · Character

Özet

Amharic language is an official language of the federal government of the Federal Democratic Republic of Ethiopia. Accordingly, there is a bulk of handwritten Amharic documents available in libraries, information centres, museums, and offices. Digitization of these documents enables to harness already available language technologies to local information needs and developments. Converting these documents will have a lot of advantages including (i) to preserve and transfer history of the country (ii) to save storage space (ii) proper handling of documents (iv) enhance retrieval of information through internet and other applications. Handwritten Amharic character recognition system becomes a challenging task due to inconsistency of a writer, variability in writing styles of different writers, relatively large number of characters of the script, high interclass similarity, structural complexity and degradation of documents due to different reasons. In order to recognize handwritten Amharic character a novel method based on deep neural networks is used which has recently shown exceptional performance in various pattern recognition and machine learning applications, but has not been endeavoured for Ethiopic script. The Convolutional neural network model is evaluated for its performance using our database that contains 132,500 datasets of handwritten Amharic characters. Common handwritten recognition systems using machine learning use a combination of both feature extractors and classifiers. Currently the use of deep learning techniques shows promising improvements for machine learning based classification tasks. Our proposed CNN model gives an accuracy of 91.83% on training data and 90.47% on validation data.

Abstract

Amharic language is an official language of the federal government of the Federal Democratic Republic of Ethiopia. Accordingly, there is a bulk of handwritten Amharic documents available in libraries, information centres, museums, and offices. Digitization of these documents enables to harness already available language technologies to local information needs and developments. Converting these documents will have a lot of advantages including (i) to preserve and transfer history of the country (ii) to save storage space (ii) proper handling of documents (iv) enhance retrieval of information through internet and other applications. Handwritten Amharic character recognition system becomes a challenging task due to inconsistency of a writer, variability in writing styles of different writers, relatively large number of characters of the script, high interclass similarity, structural complexity and degradation of documents due to different reasons. In order to recognize handwritten Amharic character a novel method based on deep neural networks is used which has recently shown exceptional performance in various pattern recognition and machine learning applications, but has not been endeavoured for Ethiopic script. The Convolutional neural network model is evaluated for its performance using our database that contains 132,500 datasets of handwritten Amharic characters. Common handwritten recognition systems using machine learning use a combination of both feature extractors and classifiers. Currently the use of deep learning techniques shows promising improvements for machine learning based classification tasks. Our proposed CNN model gives an accuracy of 91.83% on training data and 90.47% on validation data.

🔖

Bu Makaleye Atıf Yap

Abdurahman, F. (2019). Handwritten Amharic Character Recognition System Using Convolutional Neural Networks. Engineering Sciences, Cilt: 14 Sayı: 2, 71–87. https://ajindex.com/articles/986251

📄 Tam Metin PDF Okuyucu

📄

PDF görüntüleyici hazırlanıyor...

Kaynakça (12)

  1. Sarkhel, R., Das, N., Saha, A.K., and Nasipuri, M., (2016). A Multi-objective Approach Towards Cost Effective Isolated handwritten Bangla character and Digit Recognition, Pattern Recognition, 58:172-189
  2. Liang, Y., Wang, J., Zhou, S., Gong, Y., and Zheng, N., (2016). Incorporating Image Priors with Deep Convolutional Neural Networks for Image Superresolution, Neurocomputing, 194:340-347
  3. Maitra, D.S., Bhattacharya, U., and Parui, S.K., (2015). CNN based common approach to handwritten character recognition of multiple scripts, Document Analysis and Recognition (ICDAR), 2015 13th International Conference on, pp:1021-1025
  4. Shin, H.C., Roth, H.R., Gao, M., Lu, L., Xu, Z., Nogues, I., Yao, J., Mollura, D., and Summers, R.M., (2016). Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning, IEEE Transactions on Medical Imaging, 35, pp:1285-1298
  5. Bai, J., Chen, Z., Feng, B., and Xu, B., (2014). Image character recognition using deep convolutional neural network learned from different languages, 2014 IEEE International Conference on Image Processing (ICIP), pp:2560-2564
  6. Lecun, Y. and Bengio, Y., (1995). Pattern Recognition and Neural Networks, in Arbib, M.A. (Eds), The Handbook of Brain Theory and Neural Networks, MIT Press 1995
  7. Guyon, I., Schomaker, L., Plamondon, R., Liberman, M., and Janet, S., (1994). Unipen Project of On-Line Data Exchange and Recognizer Benchmarks, in proc. of 12th International. Conference on Pattern Recognition (ICPR), vol:2, pp:29–33, IEEE
  8. Yuan, A., Bai, G., Jiao, L., and Liu, Y., (2012). Offline Handwritten English Character Recognition Based On Convolutional Neural Network, in 10th IAPR International Workshop on Document Analysis Systems (DAS), pp. 125-129, doi: 10.1109/DAS.2012.61
  9. Assabie, Y. and Bigun, J., (2006). Ethiopic Character Recognition Using Direction Field Tensor, in proc.int.conf. on pattern recognition, ICPR, pp:284-287, Hong Kong
  10. Teshager, B.A., and Sethuraman, R., (2015). Artificial Neural Network Approach to the Development of OCR for Real Life Amharic Documents. International Journal of Science, Engineering and Technology Research (IJSETR), Volume:4, Issue:1, pp:2278–7798
  11. Million, M. and Jawahar, C.V., (2007). Optical character recognition of Amharic documents. African Journal of Information & Communication Technology 3(2):14
  12. Bai, J., Chen, Z., Feng, B., and Xu, B., (2014). Image Character