Malayalam Handwritten Character Recognition using CNN Architecture
Abstract
The process of encoding an input text image into a machine-readable format is called optical character recognition (OCR). The difference in characteristics of each language makes it difficult to develop a universal method that will have high accuracy for all languages. A method that produces good results for one language may not necessarily produce the same results for another language. OCR for printed characters is easier than handwritten characters because of the uniformity that exists in printed characters. While conventional methods find it hard to improve the existing methods, Convolutional Neural Networks (CNN) has shown drastic improvement in classification and recognition of other languages. However, there is no OCR model using CNN for Malayalam characters. Our proposed system uses a new CNN architecture for feature extraction and softmax layer for classification of characters. This eliminates manual designing of features that is used in the conventional methods. P-ARTS Kayyezhuthu dataset is used for training the CNN and an accuracy of 99.75% is obtained for the testing dataset meanwhile a collection of 40 real time input images yielded an accuracy of 95%.
Keywords
References
Asifullah Khan , Anabia Sohail, Umme Zahoora , and Aqsa Saeed Qureshi “A Survey of the Recent Architectures of Deep Convolutional Neural Networks”, Published in Artificial Intelligence Review, DOI: https://doi.org/10.1007/s10462-020-09825-6.
Bindu Madhuri Cheekati, Roje Spandana Rajeti (2020) “Telugu handwritten character recognition using deep residual learning”, Fourth International Conference onI-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC).
G. Ramesh, Sandeep Kumar N., H.N. Champa, (2020) “Recognition of Kannada Handwritten Words using SVM Classifier with Convolutional Neural Network”, 2020 IEEE Region 10 Symposium (TENSYMP).
Manjusha J, Ajay James, C Sharavanan, (2018) “Malayalam Handwritten Character Recognition Using AlexNet Based Architecture”, Indonesian Journal of Electrical Engineering and Informatics (IJEEI) Vol. 6, No. 4, December 2018, pp. 393~400 ISSN: 2089-3272, DOI: 10.11591/ijeei.v6i1.518.
Samatha P Salim, Ajay James, Chandra Saravnan (2019) “Proposed method to Malayalam Handwritten Character Recognition using Residual Network enhanced by multi-scaled features” 1st IEEE International Confrence on Innovations in Information and Communication Technology.
Bhagyasree P V, Ajay James, Chandra Saravnan (2019) “A Proposed Framework for Recognition of Handwritten Cursive English Characters using DAG-CNN” 1st IEEE International Confrence on Innovations in Information and Communication Technology.
YasinZamani, YaserSouri, HosseinRashidi and ShohrehKasaei. (2015).Persian Handwritten Digit Recognition by Random Forest and Convolutional Neural Networks ,9th Iranian Conference on Machine Vision and Image Processing,(November 18-19,2015;Shahid Beheshti University -Tehran, Iran.).
Shailesh Acharya, Ashok Kumar Pant, Prashnna Kumar Gyawali. (2015). “Deep Learning Based Large Scale Handwritten Devanagari Character Recognition”,9th International Conference on Software, Knowledge, Information Management and Applications (SKIMA).
Jomy John, Pramod K. V, KannanBalakrishnan.(2011) “Unconstrained Handwritten Malayalam Character Recognition using Wavelet Transform and Support vector Machine Classifier”, International Conference on Communication Technology and System Design.
Abdul Rahiman M and Rajasree M S. (2011) “An Efficient Character Recognition System for Handwritten Malayalam Characters Based on Intensity Variations” ,International Journal of Computer Theory and Engineering, Vol. 3, June.
Manju Manuel and Saidas S. R. (2015) “Handwritten Malayalam Character Recognition using Curvelet Transform and ANN”, International Journal of Computer Applications (0975 8887) Volume 121 No.6, July.
Meiyin Wu and Li Chen .(2015). “Image Recognition Based on Deep Learning”,Chinese Automation Congress (CAC).
Yujie Liu and He Huang. (2015), “Car plate character recognition using a convolutional neural network with shared hidden layers”, Chinese
Automation Congress (CAC), 2015.
PrashanthVijayaraghavan and Misha “Handwritten Tamil Recognition using a Convolutional Neural Network”, MIT Media Lab.
Anitha Mary M.O. Chackoa, Dhanya P.M. (2014).“Multiple Classifier System for Offline Malayalam Character Recognition”, International Conference on Information and Communication Technologies (ICICT).
G. Raju, Bindu S Moni, Madhu S. Nair. (2014) “A Novel Handwritten Character Recognition System Using Gradient Based Features and Run Length Count”,Sadhana Indian Academy of Sciences, Springer India, 2014, p. 1-23.
AroraSandhya, BhattacharjeeDebotosh, NasipuriMita, BasuDipak Kumar and KunduMahantapas (2008)Third international Conference on Industrial and Information Systems ICIIS,
, p. 1-6.
Ajay James, Raveena P.V and Chandran Saravanan, “Handwritten Malayalam Character Recognition using Regional Zoning and Structural Features”, International Journal of Engineering & Technology, 7 (4) (2018) 4629-4636 International Journal of Engineering & Technology Website: www.sciencepubco.com/index.php/IJET doi: 10.14419/ijet.v7i4.12551, 2018.
Jino P J ,KannanBalakrishnan, “Offline Handwritten Recognition of Malayalam District Name - A Holistic Approach”, arxiv:1705.00794.
Ajay James, Sonu Varghese K and Dr. Chandran Saravanan, “Hybrid Approach of Handwritten Malayalam Character Recognition using Geometrical and Structural Properties”, International Journal of Engineering & Technology, 7 (4) (2018) 4624-xxx International Journal of Engineering & Technology Website: www.sciencepubco.com/index.php/IJET doi: 10.14419/ijet.v7i4.11994, 2018.
Jomy John, KannanBalakrishnan, Pramod K. V. (2013) “A System for Offline Recognition of Handwritten Characters in Malayalam Script”, I.J. Image, Graphics and Signal Processing, Volume no:4 ,pg:53-59, 2013.
Meenu Alexa, Smija Das. (2016) “An Approach towards Malayalam Handwriting Recognition Using Dissimilar Classifiers”,Procedia Technology 25 224 231.
Jomy John, Kannan Balakrishnan, Pramod K. V. (2016). “Handwritten Malayalam character recognition with a novel gradient based feature descriptor and a comparative study using SVM and ELM”, International Journal on Advances in Engineering Technology and Science, 2, Issue: 3, May-June.
Nishad A, Dr. Bindu K (2013) “Malayalam OCR Systems A Survey”,International Journal of Computer Technology and Electronics Engineering (IJCTEE) Volume 3, Issue 6, December.
Jomy John, Pramod K. V, KannanBalakrishnan. (2011) “Offline Handwritten Malayalam Character Recognition Based on Chain Code Histogram”, International Conference on Emerging Trends in Electrical and Computer Technology (ICETECT).
Shanjana C, Ajay James. (2014).”Offline Recognition of Malayalam HandwrittenText”, 8th International Conference on Interdisciplinary in Engineering, INTER-ENG , Romania.
Li Chen, Song Wang, Wei Fan, Jun Sun, Satoshi Naoi. (2015). “Beyond Human Recognition: A CNN-Based Framework for Handwritten Character Recognition”, 3rd IAPR Asian Conference on Pattern Recognition, 2015.
P-ARTSKayyezhuthu https://drive.google.com/drive/folders/0B1eLyjUeuERZWUVIOU9OZm40RHc
https://en.wikipedia.org/wiki/Malayalam
Refbacks
- There are currently no refbacks.
Indonesian Journal of Electrical Engineering and Informatics (IJEEI)
ISSN 2089-3272
This work is licensed under a Creative Commons Attribution 4.0 International License.