# Tiny CNN for feature point description for document analysis: approach and dataset

arXiv: https://arxiv.org/abs/2109.04134 · HTML: https://mlsanity.com/paper/2109.04134/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 37 references that are in the map.
- First posted on arXiv 9 Sep 2021.

## Builds on (most cited first, 13 of 13)

- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size](https://mlsanity.com/paper/1602.07360/) (2016)
- [Deep metric learning using Triplet network](https://mlsanity.com/paper/1412.6622/) (2014)
- [HPatches: A benchmark and evaluation of handcrafted and learned local descriptors](https://mlsanity.com/paper/1704.05939/) (2017)
- [Working hard to know your neighbor's margins: Local descriptor learning loss](https://mlsanity.com/paper/1705.10872/) (2017)
- [Beyond triplet loss: a deep quadruplet network for person re-identification](https://mlsanity.com/paper/1704.01719/) (2017)
- [Learning to Compare Image Patches via Convolutional Neural Networks](https://mlsanity.com/paper/1504.03641/) (2015)
- [MIDV-500: A Dataset for Identity Documents Analysis and Recognition on Mobile Devices in Video Stream](https://mlsanity.com/paper/1807.05786/) (2018)
- [MIDV-2019: Challenges of the modern mobile-based document OCR](https://mlsanity.com/paper/1910.04009/) (2019)
- [Offline versus Online Triplet Mining based on Extreme Distances of Histopathology Patches](https://mlsanity.com/paper/2007.02200/) (2020)
- [Improving the HardNet Descriptor](https://mlsanity.com/paper/2007.09699/) (2020)
- [Using Deep Object Features for Image Descriptions](https://mlsanity.com/paper/1902.09969/) (2019)
- [Recognition of Images of Korean Characters Using Embedded Networks](https://mlsanity.com/paper/1911.04241/) (2019)

## Abstract (arXiv)

In this paper, we study the problem of feature points description in the context of document analysis and template matching. Our study shows that the specific training data is required for the task especially if we are to train a lightweight neural network that will be usable on devices with limited computational resources. In this paper, we construct and provide a dataset with a method of training patches retrieval. We prove the effectiveness of this data by training a lightweight neural network and show how it performs in both documents and general patches matching. The training was done on the provided dataset in comparison with HPatches training dataset and for the testing we use HPatches testing framework and two publicly available datasets with various documents pictured on complex backgrounds: MIDV-500 and MIDV-2019.