Handwritten Devanagari Character Recognition Using Modified Lenet and Alexnet Convolution Neural Networks

• Published in: Wireless personal communications Vol. 122; no. 1; pp. 349 - 378
• Main Authors: Prashanth, Duddela Sai, Mehta, R. Vasanth Kumar, Ramana, Kadiyala, Bhaskar, Vidhyacharan
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.01.2022; Springer Nature B.V
• Subjects: Artificial neural networks; Character recognition; Communications Engineering; Computer Communication Networks; Datasets; Engineering; Feature extraction; Handwriting recognition; Image segmentation; Machine learning; Networks; Neural networks; Signal,Image and Speech Processing; Computer vision; Pattern recognition; Convolution neural network; Devanagari character recognition
• ISSN: 0929-6212; 1572-834X
• DOI: 10.1007/s11277-021-08903-4

Despite many advances, Handwritten Devanagari Character Recognition (HDCR) remains unsolved due to the presence of complex characters. For HDCR, the traditional feature extraction and classification techniques are limited to the datasets developed in the respective laboratory that are not available publicly. A standard benchmarking dataset is not available for HDCR that helps to develop deep learning models. To progress the performance of HDCR, in this study, we produced a dataset of 38,750 images of Devanagari numerals, and vowels are generated and made publicly available for fellow researchers in this domain. This data is collected from more than 3000 subjects of different age groups. Each character is extracted by a segmentation technique proposed here, which is limited to this application. Experiments are conducted on the dataset; three different Convolution Neural Networks (CNN) architecture is developed. 1. CNN, 2. Modified Lenet CNN (MLCNN) and 3. Alexnet CNN (ACNN). A Modified LCNN is proposed by changing the architecture of Lenet 5 CNN. Regular Lenet 5 has tanh ( x ) as its activation function. Since the Devangari characters are nonlinear, non-linearity is introduced in the Networks by using Rectified Linear Unit. This solves the problem of vanishing gradient problem by tanh ( x ) . We achieved a recognition rate of 96% on training data and 94% on unseen data using CNN. MLCNN obtained an accuracy rate of 99% and 94% with less computational cost. Whereas, ACNN attained a recognition rate of 99% and 98% on unseen data. A series of experiments were conducted on the data with different combination splits of data and found a minimum loss of 0.001%. Such developments fill a significant percentage of the huge gap between real-world requirements and the actual performance of Devanagari recognizers.