Vision-Based Self-Checkout Terminal for Space-Constrained Retail
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Convenience stores lack the physical space for Self-Service Terminals (SSTs) and face inefficiencies in item scanning, leading to long queues and lost sales due to shoppers abandoning purchases.
Innovation Solution
A vision-based transaction terminal with three cameras captures images from different angles to recognize items, categorize them, and process transactions, enabling self-checkout for small baskets.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If Self-Service Terminals (SSTs) are installed to enable self-checkout, then checkout efficiency and customer service quality improve, but physical space requirements increase beyond what convenience stores can provide
Solution Approach 1:
The patent replaces traditional mechanical barcode scanning systems with a vision-based recognition system using cameras and image processing algorithms. The system captures images of items in the basket, automatically identifies them through computer vision, and processes transactions without requiring physical barcode labels or manual scanning devices, thereby reducing terminal size and space requirements
Solution Approach 2:
The system uses visual copying of item appearance and characteristics from captured images to identify and recognize items. Instead of requiring physical barcode labels, the vision system creates a digital representation of the item's visual features and matches it against a database, enabling identification without additional physical components
2Measurement precision
If manual barcode scanning is used at POS terminals, then item identification can be achieved, but checkout process time increases and customer queues form
Solution Approach 1:
The system performs preliminary recognition and identification of items as they are placed in the basket, continuously monitoring and updating the transaction list in real-time. This eliminates the need for a separate scanning step at checkout, as items are already identified and processed before the customer reaches the payment stage
Solution Approach 2:
The vision-based system operates continuously to capture images, process item identification, and update transaction information without interruption. Multiple cameras work in parallel to maintain continuous monitoring of the basket contents, eliminating the sequential nature of manual scanning and enabling simultaneous processing of multiple items
3Ease of operation
If store assistants are deployed to assist with scanning, then customer service quality improves, but operational costs and queue management complexity increase
Solution Approach 1:
The system enables customers to perform self-checkout automatically through vision-based item recognition. The terminal autonomously identifies items, calculates totals, and processes transactions without requiring store assistant intervention, while still providing customer-friendly interfaces and assistance options when needed
Data Source
AI summary
A vision-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.