Main Article Content
In today’s era unstaffed retail stores have become more popular in recent years and they have had a huge impact on traditional shopping habits. Unmanned retail containers play an important role in this area they can have a significant impact on the consumer shopping experience, while conventional methods based on weighing sensors are unable to detect what the customer is taking. This paper proposes a smart unstaffed retail shop scheme based on image processing, with the goal of determining if the unstaffed retail shopping style can be implemented. An end-to-end classification model trained by the method is developed for Stock Keeping Unit(SKU) counting and recognition based on a data set of images in different scenarios containing different types of SKUand the proposed solution in this study is able to achieve countingaccuracy and recognition accuracy on the test dataset, indicating that the system is efficient.
This work is licensed under a Creative Commons Attribution-NoDerivatives 4.0 International License.
CC Attribution-NoDerivatives 4.0