Edge Computing POS System Detects Ticket Swapping via Image Recognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In retail environments, existing technologies struggle to accurately detect ticket swapping, where a product label is swapped to deceive the system into scanning a cheaper item, leading to potential theft and pricing discrepancies.
Innovation Solution
The implementation of sensors, such as cameras and RFID readers, combined with machine learning models, to capture additional information about scanned products, allowing for the determination of whether the physical product matches the scanned label, using edge computing to identify features and determine product matches or mismatches.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If only barcode scanning is used at the point of sale terminal, then the system is simple and easy to operate, but it cannot detect ticket swapping and product mismatches
Solution Approach 1:
The patent combines multiple detection technologies (barcode scanning, image recognition cameras, RFID readers) into a unified point of sale system. The image recognition camera captures product images while the barcode scanner reads labels, and both data streams are processed together by machine learning models to determine if the product matches its label, enabling ticket swapping detection without requiring separate systems
Solution Approach 2:
The patent introduces machine learning models as an intermediary component that processes data from multiple sensors (cameras, barcode scanners, RFID readers) and compares the physical product characteristics with the scanned label information. This intermediary layer reconciles the different data sources and makes the final determination of product-label matching, resolving the complexity of integrating multiple detection methods
2Measurement precision
If sensors and machine learning models are added to detect ticket swapping, then detection accuracy improves, but processing time and computational resources increase
Solution Approach 1:
The patent pre-trains machine learning models with extensive product image data before deployment. During checkout, these pre-trained models can quickly compare captured product images against their trained knowledge base, enabling rapid identification and matching decisions without requiring extensive real-time computation, thus maintaining fast checkout speeds while achieving high accuracy
Solution Approach 2:
The patent implements a multi-stage detection process where the system first performs quick preliminary checks using barcode scanning and basic image recognition, then only applies more computationally intensive machine learning analysis when there are discrepancies or high-risk indicators. This partial application of complex processing reduces overall computation time while maintaining detection accuracy for problematic cases
Data Source
AI summary
Disclosed herein are systems and methods for determining whether an unknown product matches a scanned barcode during a checkout process. An edge computing device or other computer system can receive, from an overhead camera at a checkout lane, image data of an unknown product that is placed on a flatbed scanning area, identify candidate product identifications for the unknown product based on applying a classification model and/or product identification models to the image data, and determine based on the candidate product identifications, whether the unknown product matches a product associated with a barcode that is scanned at a POS terminal in the checkout lane. The classification model can be used to determine n-dimensional space feature values for the unknown product and determine which product the unknown product likely matches. The product identification models can be used to determine whether the unknown product is one of the products that are modeled.