mlsanityData to 7 Oct 2026

Document Image Binarization with Fully Convolutional Neural Networks

arXiv 1708.03276 ↗First posted 10 Aug 2017cs.CVcited by 25

Not on the map. Why?

Abstract (arXiv)

Binarization of degraded historical manuscript images is an important pre-processing step for many document processing tasks. We formulate binarization as a pixel classification learning task and apply a novel Fully Convolutional Network (FCN) architecture that operates at multiple image scales, including full resolution. The FCN is trained to optimize a continuous version of the Pseudo F-measure metric and an ensemble of FCNs outperform the competition winners on 4 of 7 DIBCO competitions. This same binarization technique can also be applied to different domains such as Palm Leaf Manuscripts with good performance. We analyze the performance of the proposed model w.r.t. the architectural hyperparameters, size and diversity of training data, and the input features chosen.

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). First posted on arXiv 10 Aug 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 4; 2023: 6; 2024: 5; 2025: 1; 2026: 6.

25 papers.

Sort:

By area:

  1. 2022DocEnTr: An End-to-End Document Image Enhancement Transformercited by 28
  2. 2024DocRes: A Generalist Model Toward Unifying Document Image Restoration Taskscited by 27
  3. 2023GDB: Gated convolutions-based Document Binarizationcited by 9
  4. 2021A Survey on Deep learning based Document Image Enhancementcited by 7
  5. 2021Light-weight Document Image Cleanup using Perceptual Losscited by 6
  6. 2022Three-stage binarization of color document images based on discrete wavelet transform and generative adversarial networkscited by 5
  7. 2023DocBinFormer: A Two-Level Transformer Network for Effective Document Image Binarizationcited by 4
  8. 2023DocStormer: Revitalizing Multi-Degraded Colored Document Images to Pristine PDFcited by 3
  9. 2024Binarizing Documents by Leveraging both Space and Frequencycited by 3
  10. 2023CCDWT-GAN: Generative Adversarial Networks Based on Color Channel Using Discrete Wavelet Transform for Document Image Binarizationcited by 2
  11. 2023Volumetric Fast Fourier Convolution for Detecting Ink on the Carbonized Herculaneum Papyricited by 2
  12. 2023A Layer-Wise Tokens-to-Token Transformer Network for Improved Historical Document Image Enhancementcited by 2
13 more
  1. 2025MFE-GAN: Efficient GAN-based Framework for Document Image Enhancement and Binarization with Multi-scale Feature Extractioncited by 2
  2. 2021LS-HDIB: A Large Scale Handwritten Document Image Binarization Datasetcited by 1
  3. 2024DELINE8K: A Synthetic Data Pipeline for the Semantic Segmentation of Historical Documentscited by 1
  4. 2026Unveiling Text in Challenging Stone Inscriptions: A Character-Context-Aware Patching Strategy for Binarizationcited by 1
  5. 2022Document Image Binarization in JPEG Compressed Domain using Dual Discriminator Generative Adversarial Networkscited by 0
  6. 2022Variational Augmentation for Enhancing Historical Document Image Binarizationcited by 0
  7. 2024Leveraging Semantic Segmentation Masks with Embeddings for Fine-Grained Form Classificationcited by 0
  8. 2024Adaptive Multi Scale Document Binarisation Using Vision Mambacited by 0
  9. 2026Benchmarking OCR Pipelines with Adaptive Enhancement for Multi-Domain Retail Bill Digitizationcited by 0
  10. 2026Bridging the Sim-to-Real Gap in Semiconductor Visual Program Synthesis via Input Binarizationcited by 0
  11. 2026ERN-Net : Evolving Reason Node-Net for Document Binarizationcited by 0
  12. 2026DR-Mamba: Automatic Inference-Time Domain Adaptation for Document Image Binarization via Sample-Conditioned Detail-Background Suppressioncited by 0
  13. 2026ENet-GP: Unified Document Image Restorationcited by 0