ShoppingTotal: A Mobile Application Utilizing Assisted Rekognition Algorithm for Intelligent Price Detection from Shelf Label Images

Creative Commons License

Can Z.

Bilgi Ve İletişim Teknolojileri Dergisi, cilt.6, sa.1, ss.57-74, 2024 (Hakemli Dergi)

Özet

ShoppingTotal is a mobile application for monitoring the shopping budget through shelf labels. Using the ShoppingTotal application, shoppers capture the shelf label image of the product to obtain the product information and view the total amount of the current shopping and the history of the previous shopping lists. For the ShoppingTotal application, the Assisted Amazon Rekognition algorithm is developed based on Amazon Rekognition’s text detection service for extracting product information from label images. The FourGroceries dataset is collected for evaluating the performance of the Assisted Amazon Rekognition algorithm over original, single-filtered, and multi-filtered images based on the image filters under the categories of sharpness, blurriness, brightness, temperature, and color. According to experiments on the FourGroceries dataset, the Assisted Amazon Rekognition algorithm’s text extraction performance is found to be better on filtered images than on original images. By applying appropriate single or multiple filters on the FourGroceries dataset, the Assisted Amazon Rekognition algorithm achieves extracting the correct price values from all experimental dataset images.