LILA-BOTI : Leveraging Isolated Letter Accumulations By Ordering Teacher Insights for Bangla Handwriting Recognition

TL;DR

This paper introduces two knowledge distillation methods, LILA-BOTI and Super Teacher LILA-BOTI, to improve Bangla handwriting recognition by addressing class imbalance and leveraging teacher insights, resulting in notable accuracy improvements.

Contribution

The paper presents novel knowledge distillation techniques specifically designed for Bangla OCR, enhancing recognition of infrequent classes and outperforming conventional methods.

Findings

Up to 3.5% increase in F1-Macro score for minor classes

Up to 4.5% increase in overall word recognition rate

Effective inter-dataset generalization on unseen data

Abstract

Word-level handwritten optical character recognition (OCR) remains a challenge for morphologically rich languages like Bangla. The complexity arises from the existence of a large number of alphabets, the presence of several diacritic forms, and the appearance of complex conjuncts. The difficulty is exacerbated by the fact that some graphemes occur infrequently but remain indispensable, so addressing the class imbalance is required for satisfactory results. This paper addresses this issue by introducing two knowledge distillation methods: Leveraging Isolated Letter Accumulations By Ordering Teacher Insights (LILA-BOTI) and Super Teacher LILA-BOTI. In both cases, a Convolutional Recurrent Neural Network (CRNN) student model is trained with the dark knowledge gained from a printed isolated character recognition teacher model. We conducted inter-dataset testing on \emph{BN-HTRd} and \emph{BanglaWriting} as our evaluation protocol, thus setting up a challenging problem where the results would better reflect the performance on unseen data. Our evaluations achieved up to a 3.5% increase in the F1-Macro score for the minor classes and up to 4.5% increase in our overall word recognition rate when compared with the base model (No KD) and conventional KD.