TLGAN: document Text Localization using Generative Adversarial Nets
This provides a practical, low-data solution for text localization in scanned receipts, though it is incremental as it builds on existing deep-learning methods.
The paper tackles text localization in digital images, a key step for optical character recognition, by introducing TLGAN, a generative adversarial network that achieves 99.83% precision and 99.64% recall on SROIE test data using only ten labeled training images.
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.