Performance Analysis of Few-Shot Learning Approaches for Bangla Handwritten Character and Digit Recognition

TL;DR

This paper introduces SynergiProtoNet, a hybrid few-shot learning model that significantly improves recognition accuracy for Bangla handwritten characters and digits, outperforming existing models across various evaluation settings.

Contribution

The paper presents SynergiProtoNet, a novel hybrid network combining clustering and embedding techniques within a prototypical framework for improved few-shot recognition of complex scripts.

Findings

SynergiProtoNet outperforms state-of-the-art models in multiple benchmarks.

The model achieves higher accuracy in cross-lingual transfer tasks.

It establishes a new benchmark for few-shot handwritten character recognition.

Abstract

This study investigates the performance of few-shot learning (FSL) approaches in recognizing Bangla handwritten characters and numerals using limited labeled data. It demonstrates the applicability of these methods to scripts with intricate and complex structures, where dataset scarcity is a common challenge. Given the complexity of Bangla script, we hypothesize that models performing well on these characters can generalize effectively to languages of similar or lower structural complexity. To this end, we introduce SynergiProtoNet, a hybrid network designed to improve the recognition accuracy of handwritten characters and digits. The model integrates advanced clustering techniques with a robust embedding framework to capture fine-grained details and contextual nuances. It leverages multi-level (both high- and low-level) feature extraction within a prototypical learning framework. We rigorously benchmark SynergiProtoNet against several state-of-the-art few-shot learning models: BD-CSPN, Prototypical Network, Relation Network, Matching Network, and SimpleShot, across diverse evaluation settings including Monolingual Intra-Dataset Evaluation, Monolingual Inter-Dataset Evaluation, Cross-Lingual Transfer, and Split Digit Testing. Experimental results show that SynergiProtoNet consistently outperforms existing methods, establishing a new benchmark in few-shot learning for handwritten character and digit recognition. The code is available on GitHub: https://github.com/MehediAhamed/SynergiProtoNet.