Automatic Cashier System Based on Meal Plate Detection Using Deep Learning

DOI

10.2991/isaeece-17.2017.79How to use a DOI?

Keywords

Automatic Cashier System, Meal Plate Detection, Deep Learning, Faster-R-CNN

Abstract

Deep learning (DL) is an important branch of machine learning (ML) that has excellent performance in recognition and detection tasks. Currently, most self-service restaurants/canteens are utilizing traditional manual cashier approaches, which suffer from the problems of error calculation, low efficiency and high labor cost. In this paper, an automatic cashier system using DL is designed to solve the problems mentioned above. This system recognizes the numbers and types of multiple plates in a meal tray with faster region based convolutional neural network (Faster-R-CNN) and automatically calculates the total price of the meal. Experimental results show the satisfying meal plate detection accuracy and high cashier speed of our system.

Copyright

© 2017, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Weibin Zheng
AU  - Shengliang Peng
AU  - Qilong Chen
AU  - Hao Ouyang
AU  - Shiheng Lin
PY  - 2017/03
DA  - 2017/03
TI  - Automatic Cashier System Based on Meal Plate Detection Using Deep Learning
BT  - Proceedings of the 2017 2nd International Symposium on Advances in Electrical, Electronics and Computer Engineering (ISAEECE 2017)
PB  - Atlantis Press
SP  - 413
EP  - 418
SN  - 2352-5401
UR  - https://doi.org/10.2991/isaeece-17.2017.79
DO  - 10.2991/isaeece-17.2017.79
ID  - Zheng2017/03
ER  -