Development of a Price Tag Detection System on Mobile Devices using Deep Learning

Abstract

Ensuring customer satisfaction is an important issue in the retail industry. The way to achieve this satisfaction is to provide a quality service. The data on the price tags on the product shelves are frequently updated. These data should be included on the price tags in their current form. Customers may encounter inaccurate information on price tags in shopping places, which causes negative results in terms of customer loyalty and satisfaction. The data on the price tags is mostly checked manually, which can cause human errors. In this study, a deep learning-based solution is proposed for fast and high accuracy detection of price tag area. One of the first and important stages of a deep learning-based price recognition system is the correct detection of the price tag area. The successful execution of this stage is important for the successful execution of the next processes (barcode reading, price reading). The proposed method has been tested on mobile phones. It is envisaged that the proposed method is applicable in its current form and can be a technical reference for similar problems in the retail industry.