# Paired Image to Image Translation for Strikethrough Removal From Handwritten Words

arXiv: https://arxiv.org/abs/2201.09633 · HTML: https://mlsanity.com/paper/2201.09633/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 31 references that are in the map.
- First posted on arXiv 24 Jan 2022.

## Builds on (most cited first, 7 of 7)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation](https://mlsanity.com/paper/1611.09326/) (2016)
- [A selectional auto-encoder approach for document image binarization](https://mlsanity.com/paper/1706.10241/) (2017)
- [Fast and Robust Symmetric Image Registration Based on Distances Combining Intensity and Spatial Information](https://mlsanity.com/paper/1807.11599/) (2018)

## Built on by (most cited first, 1 of 1)

- [Handwritten Stenography Recognition and the LION Dataset](https://mlsanity.com/paper/2308.07799/) (2023)

## Abstract (arXiv)

Transcribing struck-through, handwritten words, for example for the purpose of genetic criticism, can pose a challenge to both humans and machines, due to the obstructive properties of the superimposed strokes. This paper investigates the use of paired image to image translation approaches to remove strikethrough strokes from handwritten words. Four different neural network architectures are examined, ranging from a few simple convolutional layers to deeper ones, employing Dense blocks. Experimental results, obtained from one synthetic and one genuine paired strikethrough dataset, confirm that the proposed paired models outperform the CycleGAN-based state of the art, while using less than a sixth of the trainable parameters.