TLGAN: document Text Localization using Generative Adversarial Nets

TL;DR

TLGAN is a deep learning model that effectively localizes text in digital images with minimal training data, achieving high precision and recall, and offers a practical solution for OCR preprocessing.

Contribution

This paper introduces TLGAN, a novel GAN-based approach for document text localization that requires only a small amount of labeled data and achieves state-of-the-art performance.

Findings

Achieved 99.83% precision and 99.64% recall on SROIE dataset.

Requires only ten labeled receipt images for training.

Provides a practical, easy-to-train text localization method.

Abstract

Text localization from the digital image is the first step for the optical character recognition task. Conventional image processing based text localization performs adequately for specific examples. Yet, a general text localization are only archived by recent deep-learning based modalities. Here we present document Text Localization Generative Adversarial Nets (TLGAN) which are deep neural networks to perform the text localization from digital image. TLGAN is an versatile and easy-train text localization model requiring a small amount of data. Training only ten labeled receipt images from Robust Reading Challenge on Scanned Receipts OCR and Information Extraction (SROIE), TLGAN achieved 99.83% precision and 99.64% recall for SROIE test data. Our TLGAN is a practical text localization solution requiring minimal effort for data labeling and model training and producing a state-of-art performance.