Transfer Learning using CNN for Handwritten Devanagari Character Recognition

TL;DR

This study evaluates various pre-trained CNN models for handwritten Devanagari character recognition using transfer learning, finding Inception V3 achieves the highest accuracy while AlexNet is the fastest.

Contribution

It compares multiple pre-trained CNN architectures for Devanagari character recognition, highlighting their accuracy and training efficiency.

Findings

Inception V3 achieves 99% accuracy.

AlexNet trains faster with 98% accuracy.

Transfer learning effectively recognizes handwritten Devanagari characters.

Abstract

This paper presents an analysis of pre-trained models to recognize handwritten Devanagari alphabets using transfer learning for Deep Convolution Neural Network (DCNN). This research implements AlexNet, DenseNet, Vgg, and Inception ConvNet as a fixed feature extractor. We implemented 15 epochs for each of AlexNet, DenseNet 121, DenseNet 201, Vgg 11, Vgg 16, Vgg 19, and Inception V3. Results show that Inception V3 performs better in terms of accuracy achieving 99% accuracy with average epoch time 16.3 minutes while AlexNet performs fastest with 2.2 minutes per epoch and achieving 98\% accuracy.