Integration of YOLOv4 architecture into a mixed food price analysis as an automated cashier system
The use of deep learning in computer vision has brought remarkable progress to automation, especially in the food service sector. This study introduces an automated cashier system built on the YOLOv4 framework, designed to detect mixed food items on a tray in real-time and calculate their prices. Th...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | en |
| Published: |
IEEE
2025
|
| Subjects: | |
| Online Access: | https://umpir.ump.edu.my/id/eprint/47176/1/Integration%20of%20YOLOv4%20Architecture%20into%20a%20Mixed%20Food.pdf https://umpir.ump.edu.my/id/eprint/47176/ https://doi.org/10.1109/ICSECS65227.2025.11278968 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The use of deep learning in computer vision has brought remarkable progress to automation, especially in the food service sector. This study introduces an automated cashier system built on the YOLOv4 framework, designed to detect mixed food items on a tray in real-time and calculate their prices. The system identifies various food categories on a single tray and computes the total cost using preset pricing guidelines. Using Malaysian cuisine as a case study, it aims to shorten customer wait times, boost operational efficiency, and cut down on human errors during busy periods. YOLOv4’s fast processing speed and precise localization make it an ideal choice for this purpose, delivering consistent performance despite diverse visual challenges. The experimental results show the system’s success in achieving accurate food detection and pricing. This research underscores the potential of embedding object detection in point-of-sale setups and paves the way for future enhancements like portion-based pricing, nutritional analysis, and wider use in smart retail solutions. |
|---|