Offline Handwritten Character and Numeral Recognition: A Kernel-Based Approach

Title

Offline Handwritten Character and Numeral Recognition: A Kernel-Based Approach

Creator

Sethy A.; Patra P.K.; Nayak S.R.; Poonia R.C.

Description

Automatic character recognition for the handwritten Indic script is a challenging area for research in the field of pattern recognition. Although a great amount of research work has been reported, all the state-of-the-art methods are limited with optimal features. This article aims to suggest a well-defined recognition model which harnessed upon handwritten Odia characters and numerals by implementing a novel process of decomposition in terms of 3rd level fast discrete curvelet transform (FDCT) to get higher dimension feature vector. After that, kernel-principal component analysis (K-PCA) is considered to obtain optimal features from FDCT feature. Finally, the classification is performed by using probabilistic neural network (PNN) on a handwritten Odia character and numeral dataset from both NIT Rourkela and IIT Bhubaneswar. The outcome of the proposed scheme performs better compared to existing models with optimized Gaussian kernel-based feature sets. Copyright 2022, IGI Global.

Source

International Journal of Social Ecology and Sustainable Development, Vol-13, No. 1

Date

2022-01-01

Publisher

IGI Global

Subject

Fast Discrete Curvelet Translation (FCDT); Gaussian; Kernel-PCA; Optical Character Recognition; Principal Component Analysis; Probabilistic Neural Network (PNN)

Coverage

Sethy A., Department of Computer Science and Engineering, College of Engineering and Technology, BBSR, India; Patra P.K., Department of Computer Science and Engineering, College of Engineering and Technology, BBSR, India; Nayak S.R., Amity School of Engineering and Technology, Amity University Uttar Pradesh, Noida, India; Poonia R.C., Department of Computer Science, CHRIST University (Deemed), Bangalore, India

Rights

Restricted Access

Relation

ISSN: 19478402

Format

Online

Language

English

Type

Article

Identifier

https://doi.org/10.4018/IJSESD.295087

https://www.scopus.com/inward/record.uri?eid=2-s2.0-85147152380&doi=10.4018%2fIJSESD.295087&partnerID=40&md5=626585ba2dd6c63070020a2ce93e58d8