We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
On Development and Performance Evaluation of Novel Odia Handwritten Digit Recognition Methods.
- Authors
Majhi, Babita; Pujari, Puspalata
- Abstract
Odia is an old and recognized regional language of India and is spoken, read and written by almost 90% people of Odisha state and an appreciable part of the population of neighbouring states. Unfortunately, very little work on Odia language processing (OLP) has been carried out and reported in standard literature. Accordingly, in this paper, a sincere attempt has been made on the recognition of handwritten Odia numerals, as a part of OLP, by using a standard database (Bhowmik et al. in Proceedings of 9th international conference on information technology (ICIT’06), Bhubaneswar, 18-21 December, pp 105-110, <xref>2006</xref>) of ISI Kolkata. In this investigation, we have chosen six different transforms like the discrete Fourier transform (DFT), short-time Fourier transform, discrete cosine transform, discrete wavelet transform, S-transform (ST) and curvelet transform (CT) for feature extraction from handwritten numerals and principal component analysis for feature reduction. The standard four adaptive classifiers such as multilayered perceptron (MLP), four types of functional link artificial neural network (FLANN), radial basis function network and probabilistic neural network (PNN) are used to classify the handwritten Odia digits using the reduced extracted features from transform as inputs. The investigation made in this paper reveals that the RBF network with CT-based features and the power series FLANN with DFT features provide the best and the worst recognition performance for handwritten Odia numerals, respectively. Further, the first five best accuracy-based combined recognition systems are RBF-CT, RBF-ST, RBF-WT, PNN-CT and MLP-CT which offers percentage classification accuracy of 98.70, 96.22, 95.12, 95.10 and 93.60, respectively.
- Subjects
PERFORMANCE evaluation; FOURIER transforms; ARTIFICIAL neural networks
- Publication
Arabian Journal for Science & Engineering (Springer Science & Business Media B.V. ), 2018, Vol 43, Issue 8, p3887
- ISSN
2193-567X
- Publication type
Article
- DOI
10.1007/s13369-017-2652-6