Computer Vision Checkout System for Non-Barcoded Produce Recognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional retail store checkout systems face inefficiencies due to the inability to scan non-barcoded items, such as fruits and vegetables, and the slow process of scanning packaged products, leading to increased workloads and errors for cashiers and customers.
Innovation Solution
A computer vision-based system that uses photo images and depth sensors to recognize items as they pass through a checkout area, combining images from multiple angles to identify products and supplementing a library of pre-stored images, allowing for automatic addition to the checkout list, with audio and visual feedback for the customer or cashier, and integrating with existing barcode scanning technology for unrecognized items.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If conventional barcode scanning systems are used, then packaged products can be identified, but non-barcoded items such as fruits and vegetables cannot be recognized
Solution Approach 1:
The patent replaces the mechanical barcode scanning system with a computer vision system using cameras and image processing algorithms. This substitution enables the system to recognize both barcoded and non-barcoded items through visual identification, thereby expanding adaptability while maintaining reliability through multiple recognition methods
Solution Approach 2:
The patent creates a universal checkout system that can handle multiple types of items through a single integrated system. The computer vision system serves multiple functions: identifying barcoded items, recognizing non-barcoded produce, detecting item attributes, and providing verification, replacing the need for separate manual processes
2Measurement precision
If manual scanning of each packaged product is performed, then product identification can be achieved, but the checkout process becomes time-consuming
Solution Approach 1:
The patent implements continuous image capture and processing as items move through the checkout area. Instead of discrete scanning actions, the system continuously monitors the conveyor belt, capturing images of all items automatically, which eliminates the time required for manual scanning while maintaining accurate identification
Solution Approach 2:
The system performs preliminary image capture and processing before items reach the checkout completion point. By pre-identifying all items on the conveyor belt and calculating totals in advance, the system eliminates the time required for sequential scanning and payment calculation, significantly speeding up the checkout process
3Loss of information
If barcode alignment and scanning is required for each item, then product codes can be read, but the process requires substantial time and user attention
Solution Approach 1:
The system performs automatic image capture and processing without requiring user actions for each item. The computer vision system independently identifies items, reads codes, and processes information, eliminating the time users would spend manually aligning and scanning barcodes while ensuring complete code capture
4Adaptability or versatility
If cashiers manually identify produce items from long lists, then non-barcoded items can be processed, but errors increase and work burden increases
Solution Approach 1:
The patent replaces the manual cashier process with an automated computer vision system. The system automatically captures images of produce items, identifies them through pattern recognition, and retrieves pricing information, eliminating the need for cashiers to manually search through long produce lists and reducing both errors and workload
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
This solution significantly speeds up the checkout process, doubling the speed of each transaction, and reduces errors by enabling the recognition of non-barcoded items and packaged products, enhancing the overall efficiency and reliability of retail store checkout systems.
Implementation Method 1
all or substantially all items in a store are recognized by photo images and depth sensors, as they pass through a checkout area
Implementation Method 2
all or substantially all items in a store are recognized by photo images and depth sensors
Data Source
AI summary
A retail store automated checkout system uses images, video, or depth data to recognize products being purchased to expedite the checkout process and improve accuracy. All of a store's products, including those not sold in packages, such as fruits and vegetables, are imaged from a series of different angles and in different lighting conditions, to produce a library of images for each product. This library is used in a checkout system that takes images, video, and depth sensor readings as the products pass through the checkout area and remove bottlenecks later in the checkout process. Recognition of product identifiers or attributes such as barcode, QR code or other symbols, as well as OCR of product names, as well as the size and material of the product, can be additional or supplemental devices for identifying products being purchased. In another embodiment, an existing checkout or self-checkout scanner is enhanced with image recognition of products to achieve the same effect.