# HWNet v2: An Efficient Word Image Representation for Handwritten Documents

arXiv: https://arxiv.org/abs/1802.06194 · HTML: https://mlsanity.com/paper/1802.06194/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Feb 2018.

## Built on by (most cited first, 13 of 13)

- [Content and Style Aware Generation of Text-line Images for Handwriting Recognition](https://mlsanity.com/paper/2204.05539/) (2022)
- [RoDLA: Benchmarking the Robustness of Document Layout Analysis Models](https://mlsanity.com/paper/2403.14442/) (2024)
- [Self-Training of Handwritten Word Recognition for Synthetic-to-Real Adaptation](https://mlsanity.com/paper/2206.03149/) (2022)
- [Recognition-free Question Answering on Handwritten Document Collections](https://mlsanity.com/paper/2202.06080/) (2022)
- [ST-KeyS: Self-Supervised Transformer for Keyword Spotting in Historical Handwritten Documents](https://mlsanity.com/paper/2303.03127/) (2023)
- [Pho(SC)-CTC -- A Hybrid Approach Towards Zero-shot Word Image Recognition](https://mlsanity.com/paper/2105.15093/) (2021)
- [DSS: Synthesizing long Digital Ink using Data augmentation, Style encoding and Split generation](https://mlsanity.com/paper/2311.17786/) (2023)
- [Fetch-A-Set: A Large-Scale OCR-Free Benchmark for Historical Document Retrieval](https://mlsanity.com/paper/2406.07315/) (2024)
- [A Study of Augmentation Methods for Handwritten Stenography Recognition](https://mlsanity.com/paper/2303.02761/) (2023)
- [Keyword Spotting Simplified: A Segmentation-Free Approach using Character Counting and CTC re-scoring](https://mlsanity.com/paper/2308.03515/) (2023)
- [Enhancing Indic Handwritten Text Recognition Using Global Semantic Information](https://mlsanity.com/paper/2212.07776/) (2022)
- [Towards Robust Handwritten Text Recognition with On-the-fly User Participation](https://mlsanity.com/paper/2212.08834/) (2022)
- [Efficient Domain Adaptation for Text Line Recognition via Decoupled Language Models](https://mlsanity.com/paper/2603.28028/) (2026)

## Abstract (arXiv)

We present a framework for learning an efficient holistic representation for handwritten word images. The proposed method uses a deep convolutional neural network with traditional classification loss. The major strengths of our work lie in: (i) the efficient usage of synthetic data to pre-train a deep network, (ii) an adapted version of the ResNet-34 architecture with the region of interest pooling (referred to as HWNet v2) which learns discriminative features for variable sized word images, and (iii) a realistic augmentation of training data with multiple scales and distortions which mimics the natural process of handwriting. We further investigate the process of transfer learning to reduce the domain gap between synthetic and real domain, and also analyze the invariances learned at different layers of the network using visualization techniques proposed in the literature. Our representation leads to a state-of-the-art word spotting performance on standard handwritten datasets and historical manuscripts in different languages with minimal representation size. On the challenging IAM dataset, our method is first to report an mAP of around 0.90 for word spotting with a representation size of just 32 dimensions. Furthermore, we also present results on printed document datasets in English and Indic scripts which validates the generic nature of the proposed framework for learning word image representation.