Self-Checkout Scan-Skip Detection from Product Path and Residence Time
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems struggle to accurately detect fraudulent actions, such as scan skipping, at self-checkout terminals without relying on cooperation with the self-checkout terminal or POS system, using only captured images from a camera.
Innovation Solution
A fraud detection device that analyzes movement paths and residence times of products in predefined image areas using a camera, determining fraudulent actions based on these parameters without requiring integration with the self-checkout terminal or POS system.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If fraud detection is performed using only captured images from a camera without integration with self-checkout terminal or POS system, then system complexity and integration requirements are reduced, but detection accuracy and reliability deteriorate
Solution Approach 1:
The system divides the monitoring area into multiple image areas (first image area closest to scanner, second image area, etc.) and tracks product movement through each segment. By analyzing residence time in each segmented area and movement paths between areas, the system achieves accurate fraud detection using only camera images without needing integration with terminal systems.
Solution Approach 2:
The system pre-defines multiple image areas and establishes expected movement patterns before detection begins. By comparing actual product movement paths and residence times against these pre-established patterns, the system can detect fraudulent actions like scan skipping with high accuracy while maintaining operational independence.
2Measurement precision
If multiple image areas and movement path analysis are used to detect fraudulent actions, then detection accuracy improves, but processing complexity and computational requirements increase
Solution Approach 1:
The monitoring space is segmented into multiple image areas with specific spatial relationships to the scanner. This segmentation enables focused analysis of product movement in critical zones without requiring complex full-scene analysis, balancing detection accuracy with processing efficiency.
Solution Approach 2:
The system automatically captures images, identifies products, tracks movement paths through defined areas, and detects fraudulent actions without human intervention. The automated processing pipeline handles the computational complexity internally, providing accurate detection while maintaining simple operational interfaces.
Data Source
AI summary
A storing unit stores area information indicating positions of a plurality of image areas set in a captured image of a front region of a self-checkout terminal including a scanner. A processing unit recognizes a product from the captured image. The processing unit detects a fraudulent action related to a scanning operation for causing the scanner to scan product information attached to the product, based on a movement path of the recognized product in the plurality of image areas, and a residence time of the product in a first image area that is closest to the scanner among the plurality of image areas.