Handwritten optical character recognition by hybrid neural network training algorithm

ABSTRACT

Handwritten optical character recognition (OCR) is the renowned research area in several fields, like writers identification, bank cheques, and so on. Literature works presented the handwritten OCR for various languages. This paper proposes a hybrid neural network training algorithm for English handwritten OCR. Initially, the noise in the input image is removed using the median filter, and the image is resized. Then, the feature sets, positional, and structural descriptors are extracted from the input image. Once the feature sets are extracted, the proposed FLM-based neural network identifies the handwritten character. The FLM proposed by combining the Firefly and the Levenberg–Marquardt (LM) algorithm for training the neural network. Finally, the proposed FLM-based neural network is integrated within the feed forward neural network, and the classification of character is done with 95% accuracy based on the size of training data, number of hidden neurons and number of hidden layers.

KEYWORDS:

• FLM based neural network
• H-descriptors
• D-descriptors
• firefly algorithm
• Levenberg–Marquardt algorithm
• Optical Character Recognition
• median filter
• Feed forward neural network

Disclosure statement

No potential conflict of interest was reported by the authors.

Notes on contributors

A. K. Sampath has completed research in Department of Computer Science and Engineering, Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology, Avadi, Chennai, India. He was born on 20th August 1983 at Tiruvannamalai, Tamil Nadu, India. He received B.Tech., in Information Technology form C.Abdul Hakeem College of Engineering and Technology, Anna University, Chennai, Tamil Nadu, in the year of 2005 and obtained M.Tech., in Computer Science and Engineering degree from Ponnaiyah Ramajayam Institute of Science & Technology, Tanjore, Tamil Nadu, in the year of 2012. He has 12 years of experience in teaching. He has published more than 6 papers in SCI/Scopus indexed journals. Currently he is working as Associate professor in the Department of Computer Engineering of Rizvi College of Engineering, Mumbai. He is a lifetime member of ISTE. His research interest includes Machine Learning and System Security.

N. Gomathi has completed research in Department of Computer Science and Engineering, Jawaharlal Nehru Technical University, Hyderabad, India. She received B.E., in Computer Science Engineering and M.E., in Computer Science and Engineering degree from Anna University, Chennai, Tamil Nadu. She has 21 years of experience in teaching. She has published more than 32 papers in SCI/Scopus indexed journals. Currently she is working as Professor in the Department of Computer Engineering of Veltech Rangarajan Dr. Sagunathala R&D Institute of Science & Technology, Chennai. She is a lifetime member of ISTE. Her research interest includes Networks and System Security.