A selectional auto-encoder approach for document image binarization

Abstract

Binarization plays a key role in the automatic information retrieval from document images. This process is usually performed in the first stages of documents analysis systems, and serves as a basis for subsequent steps. Hence it has to be robust in order to allow the full analysis workflow to be successful. Several methods for document image binarization have been proposed so far, most of which are based on hand-crafted image processing strategies. Recently, Convolutional Neural Networks have shown an amazing performance in many disparate duties related to computer vision. In this paper we discuss the use of convolutional auto-encoders devoted to learning an end-to-end map from an input image to its selectional output, in which activations indicate the likelihood of pixels to be either foreground or background. Once trained, documents can therefore be binarized by parsing them through the model and applying a threshold. This approach has proven to outperform existing binarization strategies in a number of document domains.

Published in Pattern Recognition

Cited by in corpus (14)

• DE-GAN: A Conditional Generative Adversarial Network for Document Enhancement
• DeepOtsu: Document Enhancement and Binarization using Iterative Deep Learning
• Enhance to Read Better: A Multi-Task Adversarial Network for Handwritten Document Image Enhancement
• Unsupervised Neural Domain Adaptation for Document Image Binarization
• Three-stage binarization of color document images based on discrete wavelet transform and generative adversarial networks
• Two-stage generative adversarial networks for document image binarization with color noise and background removal
• A Fair Evaluation of Various Deep Learning-Based Document Image Binarization Approaches
• Optical Music Recognition: State of the Art and Major Challenges
• Defending Water Treatment Networks: Exploiting Spatio-temporal Effects for Cyber Attack Detection
• Novel and Effective CNN-Based Binarization for Historically Degraded As-built Drawing Maps
• Detection of Information Hiding at Anti-Copying 2D Barcodes
• BiNet: Degraded-Manuscript Binarization in Diverse Document Textures and Layouts using Deep Encoder-Decoder Networks
• Analysis of PDE-based binarization model for degraded document images
• SauvolaNet: Learning Adaptive Sauvola Network for Degraded Document Binarization