Robust Handwriting Recognition with Limited and Noisy Data

TL;DR

This paper presents a robust handwriting recognition system designed to perform well on limited and noisy data, specifically in maintenance logs, by combining segmentation, recognition, and data augmentation techniques.

Contribution

It introduces a novel approach tailored for noisy, limited data scenarios, improving accuracy over existing scene-text recognition methods.

Findings

Lower error rate compared to baselines

Effective handling of noisy and difficult documents

Robust performance on maintenance logs

Abstract

Despite the advent of deep learning in computer vision, the general handwriting recognition problem is far from solved. Most existing approaches focus on handwriting datasets that have clearly written text and carefully segmented labels. In this paper, we instead focus on learning handwritten characters from maintenance logs, a constrained setting where data is very limited and noisy. We break the problem into two consecutive stages of word segmentation and word recognition respectively and utilize data augmentation techniques to train both stages. Extensive comparisons with popular baselines for scene-text detection and word recognition show that our system achieves a lower error rate and is more suited to handle noisy and difficult documents