TLGAN: document Text Localization using Generative Adversarial Nets

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.

arXiv comment17 pages, three figures, 4 tables, methods for IEEE ICDAR RRC SROIE task1 leader board

References in corpus (14)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• YOLOv3: An Incremental Improvement
• Deep Residual Learning for Image Recognition
• Res2Net: A New Multi-scale Backbone Architecture
• R-FCN: Object Detection via Region-based Fully Convolutional Networks
• DSSD : Deconvolutional Single Shot Detector
• Fully Convolutional Networks for Semantic Segmentation
• Semantic Segmentation using Adversarial Networks
• Feature Pyramid Networks for Object Detection
• Texture Synthesis Using Convolutional Neural Networks
• Bag of Freebies for Training Object Detection Neural Networks
• Image Super-Resolution Using Deep Convolutional Networks
• The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation
• It GAN DO Better: GAN-based Detection of Objects on Images with Varying Quality