• Gopal D. Upadhye

Handwritten numeral recognition has been an important area in the domain of pattern classification. The task becomes even more daunting when working with non-Roman numerals. While convolutional neural networks are the preferred choice for modeling the image data, the conception of techniques to obtain faster convergence and accurate results still poses an enigma to the researchers. In this paper, we present a new method for the optimization of the traditional convolutional neural network architecture to obtain better results for Kannada numeral images. Specifically, a new strategy for choosing the CNN configuration is presented, which is based on particle swarm optimization. The optimization strategy is helpful to reduce the time required for the manual iterative approach of architecture selection. The proposed setup is trained on varying handwritten Kannada numerals. The new method is assessed on multiple standard datasets: the standard dataset of Kannada Dig-MNIST and our own custom created dataset. Significant improvements across multiple performance metrics are observed in our proposed system over the traditional CNN training setup. The improvement in results makes a strong case for relying on such method for faster and more accurate training and inference of digit classification, especially when working in the absence of transfer learning.

Numeral recognition, Particle Swarm Optimization, Convolutional Neural Networks, Kannada Numerals

"Improved Model Configuration Strategyusing Particle Swarm Optimization for Kannada Handwritten Numeral Recognition", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.8, Issue 8, page no.e454-e459, August-2021, Available :http://www.jetir.org/papers/JETIR2108544.pdf

"Improved Model Configuration Strategyusing Particle Swarm Optimization for Kannada Handwritten Numeral Recognition", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.8, Issue 8, page no. ppe454-e459, August-2021, Available at : http://www.jetir.org/papers/JETIR2108544.pdf