# ARC: A Vision-based Automatic Retail Checkout System

arXiv: https://arxiv.org/abs/2104.02832 · HTML: https://mlsanity.com/paper/2104.02832/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 30 references that are in the map.
- First posted on arXiv 7 Apr 2021.

## Builds on (most cited first, 8 of 8)

- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [On the Convergence of Adam and Beyond](https://mlsanity.com/paper/1904.09237/) (2019)
- [How Does Batch Normalization Help Optimization?](https://mlsanity.com/paper/1805.11604/) (2018)
- [SYQ: Learning Symmetric Quantization For Efficient Deep Neural Networks](https://mlsanity.com/paper/1807.00301/) (2018)

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

- [A Region-Based Deep Learning Approach to Automated Retail Checkout](https://mlsanity.com/paper/2204.08584/) (2022)
- [Retail-786k: a Large-Scale Dataset for Visual Entity Matching](https://mlsanity.com/paper/2309.17164/) (2023)

## Abstract (arXiv)

Retail checkout systems employed at supermarkets primarily rely on barcode scanners, with some utilizing QR codes, to identify the items being purchased. These methods are time-consuming in practice, require a certain level of human supervision, and involve waiting in long queues. In this regard, we propose a system, that we call ARC, which aims at making the process of check-out at retail store counters faster, autonomous, and more convenient, while reducing dependency on a human operator. The approach makes use of a computer vision-based system, with a Convolutional Neural Network at its core, which scans objects placed beneath a webcam for identification. To evaluate the proposed system, we curated an image dataset of one-hundred local retail items of various categories. Within the given assumptions and considerations, the system achieves a reasonable test-time accuracy, pointing towards an ambitious future for the proposed setup. The project code and the dataset are made publicly available.