Capsule-Based Persian/Arabic Robust Handwritten Digit Recognition Using EM Routing

TL;DR

This paper introduces a capsule network-based system for recognizing Persian/Arabic handwritten digits, demonstrating superior performance over CNNs and previous algorithms using the Hoda dataset.

Contribution

It presents a novel capsule network architecture with EM routing for Persian/Arabic digit recognition, outperforming CNNs and prior methods.

Findings

Outperforms CNN-based models on the Hoda dataset

Achieves higher accuracy than previous recognition algorithms

Demonstrates the effectiveness of capsule networks for complex script recognition

Abstract

In this paper, the problem of handwritten digit recognition has been addressed. However, the underlying language is Persian/Arabic, and the system with which this task is a capsule network (CapsNet) has recently emerged as a more advanced architecture than its ancestor, namely CNN (Convolutional Neural Network). The training of the architecture is performed using the Hoda dataset, which has been provided for Persian/Arabic handwritten digits. The output of the system clearly outperforms the results achieved by its ancestors, as well as other previously presented recognition algorithms.