Pho(SC)-CTC -- A Hybrid Approach Towards Zero-shot Word Image Recognition

TL;DR

This paper introduces Pho(SC)-CTC, a hybrid zero-shot word recognition model combining Pho(SC)Net features with CTC, demonstrating effectiveness on historical and synthetic datasets for recognizing unseen words.

Contribution

It presents a novel hybrid approach that leverages Pho(SC)Net features with CTC for zero-shot word recognition in historical documents, improving recognition of unseen words.

Findings

Effective on historical document datasets

Outperforms previous zero-shot methods

Validates approach on synthetic handwritten data

Abstract

Annotating words in a historical document image archive for word image recognition purpose demands time and skilled human resource (like historians, paleographers). In a real-life scenario, obtaining sample images for all possible words is also not feasible. However, Zero-shot learning methods could aptly be used to recognize unseen/out-of-lexicon words in such historical document images. Based on previous state-of-the-art method for zero-shot word recognition Pho(SC)Net, we propose a hybrid model based on the CTC framework (Pho(SC)-CTC) that takes advantage of the rich features learned by Pho(SC)Net followed by a connectionist temporal classification (CTC) framework to perform the final classification. Encouraging results were obtained on two publicly available historical document datasets and one synthetic handwritten dataset, which justifies the efficacy of Pho(SC)-CTC and Pho(SC)Net.