Dual Sensor Scanner Support for Self-Checkout Misuse Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Self-checkout stations lack effective detection methods for misuse such as scan avoidance, ticket switching, and facial identification due to limitations in traditional single imaging sensor systems.
Innovation Solution
An imaging device with two imaging sensors and an illumination emitter, configured for placement in various orientations, captures and decodes indicia data, captures images for facial recognition, and detects scan avoidance and ticket switching by directing overlapping fields of view through a transmissive window.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a single imaging sensor is used, then the device complexity is reduced, but the ability to detect scan avoidance, ticket switching, and perform facial identification is insufficient
Solution Approach 1:
The imaging system is segmented into two distinct imaging sensors: a first imaging sensor for decoding indicia data (barcodes, QR codes) and a second imaging sensor for capturing images including facial recognition. This segmentation allows each sensor to be optimized for its specific function, improving overall detection capability while maintaining manageable system complexity through specialized components.
Solution Approach 2:
The imaging device achieves multi-functionality by integrating two imaging sensors that can perform multiple tasks: the first sensor handles indicia decoding while the second sensor captures images for facial recognition, scan avoidance detection, and ticket switching detection. This universal approach allows a single device to perform diverse security and verification functions that would otherwise require separate systems.
2Reliability
If traditional single imaging sensor scanners are used, then the manufacturing cost is lower, but the ability to detect misuse and perform identification is limited
Solution Approach 1:
The system divides the imaging functionality into two separate sensors with distinct roles: one dedicated to reading codes and another dedicated to capturing visual evidence including faces and item placement. This segmentation improves misuse detection accuracy by ensuring each sensor is optimized for its specific detection task, while the modular design facilitates easier manufacturing and assembly compared to a monolithic complex sensor system.
Solution Approach 2:
The housing structure serves as an intermediary that positions and integrates the two imaging sensors, illumination emitter, and optical components. This intermediary framework simplifies manufacturing by providing a pre-configured mounting structure that aligns all components correctly, reducing assembly complexity despite the increased functional capability of the dual-sensor system.
3Reliability
If the second imaging sensor is positioned in the bottom portion of the housing, then facial recognition and scan avoidance detection are improved, but the housing space requirements increase
Solution Approach 1:
The second imaging sensor is positioned in the bottom portion of the housing and directed upwardly at an angle between 10 and 45 degrees relative to the horizontal plane, rather than being positioned horizontally. This angular orientation in a different dimension allows the sensor to capture facial images and detect scan avoidance effectively while utilizing vertical space more efficiently, reducing the overall housing volume requirement compared to a horizontal sensor arrangement.
Solution Approach 2:
The imaging device directs the second FOV upwardly with specific angular ranges (10-45 degrees) tailored to the local requirement of capturing facial images and detecting scan avoidance. This localized angular optimization ensures that the sensor achieves maximum detection capability in the critical upward direction while minimizing the housing space required in other directions, creating an efficient spatial configuration.
4Area of stationary object
If the first FOV is directed downwardly at an angle, then indicia decoding coverage is improved, but the alignment precision with the scanning surface must be maintained
Solution Approach 1:
The first imaging sensor is positioned to direct the first FOV downwardly at an adjustable angle between 5 and 20 degrees relative to the horizontal plane. This dynamic angular positioning allows the sensor to cover a larger area of the scanning surface for indicia decoding while the housing structure provides mechanical guidance to maintain alignment within acceptable tolerances, balancing coverage area with alignment precision requirements.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enhances detection capabilities for misuse in self-checkout systems by enabling effective facial recognition, scan avoidance, and ticket switching detection, improving security and accuracy in retail environments.
Implementation Method 1
The first imaging assembly includes a first imaging sensor having a first field of view (FOV) extending through the window. The first imaging assembly is configured to decode indicia data captured within the first FOV.
Implementation Method 2
The second imaging assembly includes a second imaging sensor having a second field of view (FOV) extending through the window. The second imaging assembly is configured to capture images in the second FOV.
Implementation Method 3
The illumination emitter is configured to generate illumination light visible through the window.
Data Source
AI summary
An imaging device includes a housing having an optically transmissive window, a first imaging assembly, and a second imaging assembly. A second imaging sensor of the second imaging assembly is positioned within a bottom portion of the housing height and a front portion of the housing depth. The second imaging sensor may be positioned in either a landscape orientation or a portrait orientation. A downstream region is defined between a downstream side of a first field of view of the first imaging sensor and a downstream side of a second field of view of the second imaging sensor to allow the imaging device to determine whether an indicia associated with a product captured within the downstream region was previously captured in the first field of view, thereby facilitating detection of scan avoidance or ticket switching.