Two-Stage Generative Adversarial Networks for Document Image Binarization with Color Noise and Background Removal

by   Sungho Suh, et al.

Document image enhancement and binarization methods are often used to improve the accuracy and efficiency of document image analysis tasks such as text recognition. Traditional non-machine-learning methods are constructed on low-level features in an unsupervised manner but have difficulty with binarization on documents with severely degraded backgrounds. Convolutional neural network-based methods focus only on grayscale images and on local textual features. In this paper, we propose a two-stage color document image enhancement and binarization method using generative adversarial neural networks. In the first stage, four color-independent adversarial networks are trained to extract color foreground information from an input image for document image enhancement. In the second stage, two independent adversarial networks with global and local features are trained for image binarization of documents of variable size. For the adversarial neural networks, we formulate loss functions between a discriminator and generators having an encoder-decoder structure. Experimental results show that the proposed method achieves better performance than many classical and state-of-the-art algorithms over the Document Image Binarization Contest (DIBCO) datasets, the LRDE Document Binarization Dataset (LRDE DBD), and our shipping label image dataset.



There are no comments yet.


page 2

page 4

page 10

page 12


DE-GAN: A Conditional Generative Adversarial Network for Document Enhancement

Documents often exhibit various forms of degradation, which make it hard...

Predicting Rapid Fire Growth (Flashover) Using Conditional Generative Adversarial Networks

A flashover occurs when a fire spreads very rapidly through crevices due...

DeepOtsu: Document Enhancement and Binarization using Iterative Deep Learning

This paper presents a novel iterative deep learning framework and apply ...

Deeply Matting-based Dual Generative Adversarial Network for Image and Document Label Supervision

Although many methods have been proposed to deal with nature image super...

A selectional auto-encoder approach for document image binarization

Binarization plays a key role in the automatic information retrieval fro...

Geometric Surface Image Prediction for Image Recognition Enhancement

This work presents a method to predict a geometric surface image from a ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.