Vision-Based Self-Checkout Terminal for Small-Basket Item Recognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Convenience stores lack the physical space to install Self-Service Terminals (SSTs) for self-checkouts, leading to busy queues and potential losses due to shoppers abandoning items without completing purchases, as traditional barcode scanning is inconvenient for small baskets and not all items can be labeled.
Innovation Solution
A vision-based frictionless self-checkout system using three cameras to capture images of items from different angles, processing them to determine item locations, categorize, and assign unique identifiers, allowing for accurate item recognition and transaction processing without the need for physical labels or large space-consuming terminals.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If traditional barcode scanning is used at self-service terminals, then item identification can be achieved, but the system requires large physical space and complex infrastructure that convenience stores cannot accommodate
Solution Approach 1:
The patent replaces traditional mechanical barcode scanning systems with a vision-based identification system using cameras and image processing algorithms. The system captures images of items in the shopping basket and automatically identifies them through computer vision technology, eliminating the need for physical barcode scanners and large self-service terminal infrastructure.
Solution Approach 2:
The system creates digital copies (images) of physical items and processes these copies for identification. By capturing visual information of items through cameras and analyzing the image data, the system identifies items without requiring physical interaction with barcodes or labels, thereby reducing the need for complex scanning hardware and space.
2Measurement precision
If store assistants are deployed to scan items manually, then accurate item identification is achieved, but queue congestion increases and transaction efficiency decreases
Solution Approach 1:
The system enables automatic item identification and transaction processing without human intervention. The vision-based system autonomously captures images of items, processes them through image recognition algorithms, and completes transactions automatically, replacing manual scanning by store assistants and eliminating queue congestion while maintaining high transaction throughput.
Solution Approach 2:
The system performs item identification and transaction preparation in advance by continuously monitoring and recognizing items as they are placed in the shopping basket. This preliminary processing allows transactions to be completed rapidly when the customer reaches the checkout point, increasing overall transaction throughput without sacrificing identification accuracy.
3Adaptability or versatility
If paper barcode labels are attached to items, then item codes can be scanned, but items unsuitable for labeling cannot be processed and the process becomes inconvenient
Solution Approach 1:
The patent replaces the mechanical process of attaching physical barcode labels with a non-contact vision-based identification system. Cameras capture images of items directly, and computer vision algorithms extract identification information from the item's visual appearance, packaging, or inherent features, enabling processing of items that cannot accommodate paper labels while simplifying the overall operation.
Data Source
AI summary
A vison-based self-checkout terminal is provided. Purchased items are placed on a base and multiple cameras take multiple images of each item placed on the base. A location for each item placed on the base is determined along with a depth and the dimensions of each item at its given location on the base. Each item's images are then cropped, and item recognition is performed for each item on that item's cropped images with that item's corresponding depth and dimension attributes. An item identifier for each item is obtained along with a corresponding price and a transaction associated with items are completed.