# Siamese based Neural Network for Offline Writer Identification on word level data

arXiv: https://arxiv.org/abs/2211.14443 · HTML: https://mlsanity.com/paper/2211.14443/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 76 references that are in the map.
- First posted on arXiv 17 Nov 2022.

## Builds on (most cited first, 17 of 17)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Deep metric learning using Triplet network](https://mlsanity.com/paper/1412.6622/) (2014)
- [SigNet: Convolutional Siamese Network for Writer Independent Offline Signature Verification](https://mlsanity.com/paper/1707.02131/) (2017)
- [Unsupervised Feature Learning for Writer Identification and Writer Retrieval](https://mlsanity.com/paper/1705.09369/) (2017)
- [Handwriting Biometrics: Applications and Future Trends in e-Security and e-Health](https://mlsanity.com/paper/2202.12760/) (2022)
- [FragNet: Writer Identification using Deep Fragment Networks](https://mlsanity.com/paper/2003.07212/) (2020)
- [DeepWriterID: An End-to-end Online Text-independent Writer Identification System](https://mlsanity.com/paper/1508.04945/) (2015)
- [DeepWriter: A Multi-Stream Deep CNN for Text-independent Writer Identification](https://mlsanity.com/paper/1606.06472/) (2016)
- [GR-RNN: Global-Context Residual Recurrent Neural Networks for Writer Identification](https://mlsanity.com/paper/2104.05036/) (2021)
- [Deep Adaptive Learning for Writer Identification based on Single Handwritten Word Images](https://mlsanity.com/paper/1809.10954/) (2018)
- [Text-independent writer identification using convolutional neural network](https://mlsanity.com/paper/2009.04877/) (2020)
- [Semi-supervised Feature Learning For Improving Writer Identification](https://mlsanity.com/paper/1807.05490/) (2018)

## Built on by (most cited first, 2 of 2)

- [Image-based Freeform Handwriting Authentication with Energy-oriented Self-Supervised Learning](https://mlsanity.com/paper/2408.09676/) (2024)
- [CSSL-RHA: Contrastive Self-Supervised Learning for Robust Handwriting Authentication](https://mlsanity.com/paper/2307.11100/) (2023)

## Abstract (arXiv)

Handwriting recognition is one of the desirable attributes of document comprehension and analysis. It is concerned with the documents writing style and characteristics that distinguish the authors. The diversity of text images, notably in images with varying handwriting, makes the process of learning good features difficult in cases where little data is available. In this paper, we propose a novel scheme to identify the author of a document based on the input word image. Our method is text independent and does not impose any constraint on the size of the input image under examination. To begin with, we detect crucial components in handwriting and extract regions surrounding them using Scale Invariant Feature Transform (SIFT). These patches are designed to capture individual writing features (including allographs, characters, or combinations of characters) that are likely to be unique for an individual writer. These features are then passed through a deep Convolutional Neural Network (CNN) in which the weights are learned by applying the concept of Similarity learning using Siamese network. Siamese network enhances the discrimination power of CNN by mapping similarity between different pairs of input image. Features learned at different scales of the extracted SIFT key-points are encoded using Sparse PCA, each components of the Sparse PCA is assigned a saliency score signifying its level of significance in discriminating different writers effectively. Finally, the weighted Sparse PCA corresponding to each SIFT key-points is combined to arrive at a final classification score for each writer. The proposed algorithm was evaluated on two publicly available databases (namely IAM and CVL) and is able to achieve promising result, when compared with other deep learning based algorithm.