# Hybrid Feature Learning for Handwriting Verification

## TL;DR

This paper introduces a hybrid deep learning architecture combining auto-learned and human-engineered features for handwriting verification, achieving high accuracy and outperforming existing methods on large datasets.

## Contribution

It presents a novel HDL architecture that integrates CNN, autoencoders, GSC, and SIFT features for improved handwriting verification performance.

## Key findings

- Achieves 99.7% accuracy on seen writer dataset
- Attains 92.16% accuracy on shuffled writer dataset
- Performs comparably to state-of-the-art on unseen writer dataset

## Abstract

We propose an effective Hybrid Deep Learning (HDL) architecture for the task of determining the probability that a questioned handwritten word has been written by a known writer. HDL is an amalgamation of Auto-Learned Features (ALF) and Human-Engineered Features (HEF). To extract auto-learned features we use two methods: First, Two Channel Convolutional Neural Network (TC-CNN); Second, Two Channel Autoencoder (TC-AE). Furthermore, human-engineered features are extracted by using two methods: First, Gradient Structural Concavity (GSC); Second, Scale Invariant Feature Transform (SIFT). Experiments are performed by complementing one of the HEF methods with one ALF method on 150000 pairs of samples of the word "AND" cropped from handwritten notes written by 1500 writers. Our results indicate that HDL architecture with AE-GSC achieves 99.7% accuracy on seen writer dataset and 92.16% accuracy on shuffled writer dataset which out performs CEDAR-FOX, as for unseen writer dataset, AE-SIFT performs comparable to this sophisticated handwriting comparison tool.