Automated shopping system using computer vision
- PDF / 1,269,421 Bytes
- 11 Pages / 439.37 x 666.142 pts Page_size
- 15 Downloads / 235 Views
Automated shopping system using computer vision Nemer Odeh 1
& Cem Direkoglu
1
Received: 11 August 2019 / Revised: 22 July 2020 / Accepted: 28 July 2020 # Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract
The shopping experiment made by amazon go in USA is one of the most interesting applications of computer vision recently. They allow you to shop and automatically charge your virtual card for whatever goods you purchased using cameras and wireless systems, so no checkouts or waiting lines are required. However, amazon didn’t reveal yet the details of how their system components are implemented. In this paper, we introduce a complete system for computer vision based automated shopping. The proposed system contains barcode scanning of objects, data registration, image capturing for offline training stage, motion (change) detection, CNN and SVM for object classification and charging/discharging customers. Our system can be integrated with the wireless data transmission to do the whole shopping process. First, the proposed method extracts the objects’ barcodes to register their details, and take sample images of objects for classifier training. We employ a pre-trained CNN (i.e. ResNet50) for feature extraction and a multiclass SVM for training. After training our classifier, we have a real-time operation stage (i.e. test stage). We assume that a camera is embedded above products on each shelf to capture videos of the products. We employ a change detector to understand any added or removed items. If the item is removed from or added to the shelve, the moving object is input to CNN feature extractor, and then SVM classifier for identification and pricing. Results show that the proposed system is fast and effective. Keywords Automated shopping experiment . Computer vision . Convolutional neural networks . And support vector machines
* Nemer Odeh [email protected] Cem Direkoglu [email protected]
1
Department of Electrical & Electronics Engineering, Middle East Technical University, Northern Cyprus Campus, Kalkanli, Guzelyurt, TRNC, Mersin 10, Turkey
Multimedia Tools and Applications
1 Introduction The first real world amazon grocery store which is named by ‘amazon go’ had been opened in 2016 to test it on the employees before extending it to the public in 2018. As Amazon stated, the aim of this application is not to retail employees rather than offering a new convenient shopping environment without the usual crowd noises existed in normal stores. The human act here will be represented by setting up the products, monitoring the market in back stages, and checking customer’s IDs at the entrance. This project can be considered as a basement for future plans by amazon since they invested almost $13.5 billion to scoop up more than 460 Whole Foods locations, and hence, this application will become an interesting phenomenon in the near future [1]. The store works as the following; first, you download the amazon go application on your mobile phone to register your information; i.e. your
Data Loading...
