DeepOtsu: Document Enhancement and Binarization using Iterative Deep Learning

Abstract

This paper presents a novel iterative deep learning framework and apply it for document enhancement and binarization. Unlike the traditional methods which predict the binary label of each pixel on the input image, we train the neural network to learn the degradations in document images and produce the uniform images of the degraded input images, which allows the network to refine the output iteratively. Two different iterative methods have been studied in this paper: recurrent refinement (RR) which uses the same trained neural network in each iteration for document enhancement and stacked refinement (SR) which uses a stack of different neural networks for iterative output refinement. Given the learned uniform and enhanced image, the binarization map can be easy to obtain by a global or local threshold. The experimental results on several public benchmark data sets show that our proposed methods provide a new clean version of the degraded image which is suitable for visualization and promising results of binarization using the global Otsu's threshold based on the enhanced images learned iteratively by the neural network.

Accepted by Pattern Recognition

References in corpus (3)

• A selectional auto-encoder approach for document image binarization
• Robust Regression For Image Binarization Under Heavy Noises and Nonuniform Background
• Beyond pixels and regions: A non local patch means (NLPM) method for content-level restoration, enhancement, and reconstruction of degraded document images

Cited by in corpus (14)

• Enhance to Read Better: A Multi-Task Adversarial Network for Handwritten Document Image Enhancement
• Adaptive binarization based on fuzzy integrals
• Boosting offline handwritten text recognition in historical documents with few labeled lines
• Unsupervised Neural Domain Adaptation for Document Image Binarization
• Deep Neural Networks for Automatic Grain-matrix Segmentation in Plane and Cross-polarized Sandstone Photomicrographs
• Three-stage binarization of color document images based on discrete wavelet transform and generative adversarial networks
• Personalizing image enhancement for critical visual tasks: improved legibility of papyri using color processing and visual illusions
• Two-stage generative adversarial networks for document image binarization with color noise and background removal
• DUET: Detection Utilizing Enhancement for Text in Scanned or Captured Documents
• Light-weight Document Image Cleanup using Perceptual Loss
• A Fair Evaluation of Various Deep Learning-Based Document Image Binarization Approaches
• SauvolaNet: Learning Adaptive Sauvola Network for Degraded Document Binarization
• Analysis of PDE-based binarization model for degraded document images
• BiNet: Degraded-Manuscript Binarization in Diverse Document Textures and Layouts using Deep Encoder-Decoder Networks