Product Identification Based on Unsupervised Detection Keypoint Alignment and Convolutional Neural Networks

Kang Le

2019

Abstract

Traditional shelf auditing is a manual audit. With the development of computer vision and deep learning technology, it has become possible to use machine automatic image recognition instead of manual auditing. Existing product identification is based on the use of two-dimensional code recognition and radio frequency identification (RFID), which relies on hardware and is relatively expensive. The training data of product identification is difficult to collect. This paper proposes a product identification method based on convolutional neural network, and explores how to effectively obtain the product data sets. At the same time, it introduces the unsupervised keypoint detection alignment method for the product detection part, and proves that it can improve the correct rate of product identification.

Paper Citation

in Harvard Style

Le K. (2019). Product Identification Based on Unsupervised Detection Keypoint Alignment and Convolutional Neural Networks.In Proceedings of the International Conference on Advances in Computer Technology, Information Science and Communications - Volume 1: CTISC, ISBN 978-989-758-357-5, pages 160-165. DOI: 10.5220/0008099201600165

in Bibtex Style

@conference{ctisc19,
author={Kang Le},
title={Product Identification Based on Unsupervised Detection Keypoint Alignment and Convolutional Neural Networks},
booktitle={Proceedings of the International Conference on Advances in Computer Technology, Information Science and Communications - Volume 1: CTISC,},
year={2019},
pages={160-165},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0008099201600165},
isbn={978-989-758-357-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the International Conference on Advances in Computer Technology, Information Science and Communications - Volume 1: CTISC,
TI - Product Identification Based on Unsupervised Detection Keypoint Alignment and Convolutional Neural Networks
SN - 978-989-758-357-5
AU - Le K.
PY - 2019
SP - 160
EP - 165
DO - 10.5220/0008099201600165