Barcode Dimension Detection for POS Ticket Switching Prevention
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current image-based scanners face challenges in efficiently detecting and preventing ticket switching at point-of-sale (POS) systems, as they require significant processing power, large datasets, and remote cloud processing, which strains IT architecture and increases costs.
Innovation Solution
A method using a barcode reader to determine object dimensions by identifying barcode data and comparing it to physical features, allowing for local detection of improper object scans without the need for extensive image or video data transmission, utilizing geometric transformations and reference dimension models.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If CNN-based image processing is used to detect ticket switching, then detection accuracy is improved, but processing complexity and computational cost increase
Solution Approach 1:
The patent extracts only the essential barcode information and its spatial relationship with physical features from the complete image data. Instead of processing entire images through complex CNNs, the system extracts barcode location, dimensions, and orientation data, then compares this extracted information against reference data to detect ticket switching. This extraction approach maintains detection accuracy while dramatically reducing processing complexity.
Solution Approach 2:
The patent segments the detection task into distinct components: barcode identification, physical feature detection, dimension measurement, and comparison against reference data. This segmentation allows each component to be handled by simple, dedicated algorithms rather than a single complex CNN, reducing overall processing complexity while maintaining accuracy through systematic analysis.
2Measurement precision
If large datasets of images are used to train CNN models, then detection capability is improved, but memory requirements and data storage costs increase
Solution Approach 1:
The patent extracts only the essential barcode information and spatial relationships from complete images, creating a reduced representation that contains all necessary detection data. This extracted information (barcode location, dimensions, orientation relative to physical features) is sufficient for detection without requiring the full original images, thereby reducing data storage requirements while maintaining detection capability.
Solution Approach 2:
Instead of storing and processing large datasets of complete images to train detection models, the patent inverts the approach by pre-extracting and storing only the essential barcode and spatial relationship data as reference information. This inverted approach eliminates the need for large training datasets while maintaining detection accuracy through direct comparison of extracted features.
3Power
If cloud-based processing is used for image analysis, then processing power is improved, but data transmission time and IT architecture strain increase
Solution Approach 1:
The patent extracts all necessary detection information locally at the point-of-sale terminal before any potential cloud transmission. By extracting barcode data, physical feature locations, and dimensional measurements locally, the system eliminates the need to transmit large image datasets to the cloud for processing. This local extraction approach provides immediate processing results while avoiding data transmission time and IT architecture strain.
4Measurement precision
If additional processing beyond typical decode processors is implemented, then detection accuracy is improved, but implementation cost and processing time increase
Solution Approach 1:
The patent segments the processing into simple, discrete operations that can be performed by standard decode processors: barcode identification, physical feature detection, dimension measurement, and data comparison. These segmented operations use basic computational tasks rather than complex neural network processing, achieving detection accuracy without requiring additional specialized processing hardware or time.
Data Source
AI summary
Methods and systems for using barcodes to determine item dimensions are disclosed herein. An example method includes a scanner identifying a barcode in an image of an object, and determining a datum associated with the barcode. A physical feature of the object located outside of the barcode is identified. A comparison of the datum associated with the barcode to the physical feature is made; and, in response, at least one dimension of the object is determined.