TY - GEN
T1 - Enhancing Minimarket Customer Experience Through YOLOv8-Powered Checkout Systems
AU - Arana-Del-Carpio, Sebastian
AU - Becerra-Bisso, Luis
AU - Ugarte, Willy
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026.
PY - 2026
Y1 - 2026
N2 - In Lima, Peru, minimarkets are vital, providing essential goods to a growing population. However, slow payment processes lead to long lines and frustrated customers, impacting satisfaction and profitability. The main issue is the slow, error-prone manual item scanning at the checkout. Addressing this inefficiency can enhance economic impact, customer satisfaction, and operational efficiency. Despite the benefits, implementing object detection technology faces challenges such as technological complexity, integration issues, diverse product ranges, and high costs. Previous solutions failed due to inadequate technology, high costs, poor integration, and user resistance. This paper proposes using YOLOv8, a state-of-the-art object detection model, for its precision, real-time processing, cost-effectiveness, and easy integration. This work includes custom hardware, an integration layer, and a user interface, with the aim of reducing checkout times, achieving over 94% product recognition accuracy, and improving customer satisfaction. Initial tests show promising results in speed, accuracy, and customer feedback.
AB - In Lima, Peru, minimarkets are vital, providing essential goods to a growing population. However, slow payment processes lead to long lines and frustrated customers, impacting satisfaction and profitability. The main issue is the slow, error-prone manual item scanning at the checkout. Addressing this inefficiency can enhance economic impact, customer satisfaction, and operational efficiency. Despite the benefits, implementing object detection technology faces challenges such as technological complexity, integration issues, diverse product ranges, and high costs. Previous solutions failed due to inadequate technology, high costs, poor integration, and user resistance. This paper proposes using YOLOv8, a state-of-the-art object detection model, for its precision, real-time processing, cost-effectiveness, and easy integration. This work includes custom hardware, an integration layer, and a user interface, with the aim of reducing checkout times, achieving over 94% product recognition accuracy, and improving customer satisfaction. Initial tests show promising results in speed, accuracy, and customer feedback.
KW - YOLO
KW - data augmentation
KW - object detection
KW - real-time processing
UR - https://www.scopus.com/pages/publications/105010832989
U2 - 10.1007/978-981-96-8889-0_43
DO - 10.1007/978-981-96-8889-0_43
M3 - Contribución a la conferencia
AN - SCOPUS:105010832989
SN - 9789819688883
T3 - Lecture Notes in Computer Science
SP - 506
EP - 518
BT - Advances and Trends in Artificial Intelligence. Theory and Applications - 38th International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems, IEA/AIE 2025, Proceedings
A2 - Fujita, Hamido
A2 - Watanobe, Yutaka
A2 - Ali, Moonis
A2 - Wang, Yinglin
PB - Springer Science and Business Media Deutschland GmbH
T2 - 38th International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems, IEA/AIE 2025
Y2 - 1 July 2025 through 4 July 2025
ER -