Abstract
The broad application area and the accompanying challenges make machine learning-based recognition of handwritten scripts a demanding field. Individuals’ writing practices and inherent variations in the size, shape, and tilt of the characters may increase the difficulty level. The deep convolutional neural network (DCNN) models have been a great success in solving pattern recognition problems, but at the expense of a considerable number of trainable parameters and heavy computational loads. The proposed work addresses these problems by using the shifted window (SWIN) transformer method for the first time to recognize handwritten Devanagari numerals. In the presented model, the SWIN transformer is finely tuned to withstand the popular DCNN models such as VGG-16Net, ResNet-50, and DenseNet-121 in terms of recognition accuracy, space requirement, and computational complexity. The model successfully attains the recognition accuracy of 99.20% with just 0.218 million trainable parameters and 0.0912 giga floating-point operations per second (FLOPs). This suggests the validity and soundness of the proposed model for recognizing handwritten Devanagari numerals.