Cloud goods recognition system based on PCA and SVM

Abstract

In this paper, an intelligent inventory management system for vending machines based on image recognition has been proposed. The outside image of a vending machine goods cabinet is obtained by a camera installed on a lifted mechanism of the machine, whenever a good reloading or a buying action has been done by the routine operator or the costumer respectively. That image is labeled with the vending machine ID and forwarded to a Cloud Goods Recognition Center (CGRC). It is firstly recognized by employing the cloud goods recognition algorithm based on Principal Component Analysis (PCA) and Support Vector Machine (SVM) and then relabeled with the classified item name, items unit price by accessing the item samples database. The relabeled result is finally returned to the vending machine for its inventory updating. The experiments show that excellent classification results with more than 96% of images, correctly.