Open Access Open Access  Restricted Access Subscription Access

AMSHAM - Handwritten Malayalam Fraction Recognition Using TensorFlow

Ashna Gopi, Dilsha Das T P, Naseem Abdulla, Sooraj M V, Dilna P.M.

Abstract


Handwritten text recognition is much harder com- pared to printed text recognition. Even though many works are done on recognizing other languages, there are no works on implementing CNN on handwritten Malayalam fractions. This paper aims to preserve Malayalam fractions from being extinct. The proposed system converts Malayalam handwritten fractions into a machine-encoded format using the CNN algorithm and also translates it to English numerals. Here handwriting recognition is done with the help of TensorFlow. The proposed methods are dataset creation, dataset labeling, feature extraction, classifica- tion, etc. We have got the best accuracy about 98.26%. We have done mobile applications facile for the users to operate. We used React Native for the front end and FastAPI as the back end.


Full Text:

PDF

References


Rohan Vaidya , Darshan Trivedi , Sagar Satra, “Handwritten Character Recognition Using Deep-Learning,” 2nd International Conference on Inventive Communication and Computational Technologies (ICICCT 2018), 2018.

Thi Thi Zin, Moe Zet Pwint, Shin Thant, A Mobile Application for Offline Handwritten Character Recognition, 2020 IEEE 9th Global Conference on Consumer Electronics (GCCE), 2020.

K. Swetha and Y. Hithaishi and N.L. Tejaswini and P. Parthasaradhi and P.V. Venkateswara Rao, “Handwritten Digit Recognition Us- ing OPENCV and CNN,” International Journal of Creative Research Thoughts (IJCRT), 2021.

Muhammad Parvez Quamar. Mayank Jain, Gagandeep Kaur, and Harshit Gupta, “ Handwritten digit recognition using CNN,” International Conference on Innovative Practices in Technology and Management (ICIPTM), 2021.

R. Vijaya Kumar Reddy, Dr. B. Srinivasa Rao, K. Prudvi Raju, “ Hand- written Hindi Digits Recognition Using Convolutional Neural Network with RMSprop Optimization,” Proceedings of the Second International Conference on Intelligent Computing and Control Systems (ICICCS), 2018.

Hubert Cecotti “ Handwritten Digit Recognition of Indian Script: a cascade of distance approach,” International Joint Conference on Neural Networks (IJCNN) 2015.

N. Shobha Rani, Ashwini P.S “ Standardised Framework For Hand- written and Printed Kannada Numeral Recognition and Translating using Probabilistic Neural Network,” IJISET- International Journal of Innovative Science, Engineering and Technology.

T. Gunawan, A. Noor, and M. Kartiwi, “Development of English handwritten recognition using deep neural network,” Indonesian Journal of Electrical Engineering and Computer Science, vol. 10, pp. 562–568, 05 2018.

R. Vaidya, D. Trivedi, S. Satra, and P. M. Pimpale, “Handwritten character recognition using deep-learning,” in 2018 Second International Conference on Inventive Communication and Computational Technolo- gies (ICICCT), April 2018, pp. 772–775.

A. Yuan, G. Bai, P. Yang, Y. Guo, and X. Zhao, “Handwritten English word recognition based on convolutional neural networks,” in 2012 International Conference on Frontiers in Handwriting Recognition, Sep. 2012, pp. 207–212

K. Dutta, P. Krishnan, M. Mathew, and C. V. Jawahar, “Offline hand- writing recognition on Devanagari using a new benchmark dataset,” in 2018 13th IAPR International Workshop on Document Analysis Systems (DAS), April 2018, pp. 25–30.

C. Shanjana and A. James, “Offline recognition of Malayalam handwrit- ten text,” Procedia Technology, vol. 19, pp. 772–779, 12 2015.


Refbacks

  • There are currently no refbacks.