Machine Vision Checkout Tallying for Faster Item Recognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current retail checkout systems are inefficient and prone to repetitive motion injuries due to the need for manual handling and scanning of items, with limitations on processed object size and incompatibility with existing systems, and often rely on complex or expensive equipment for object recognition.
Innovation Solution
A machine vision system that captures images of objects on a conveyor belt or counter before processing, using optical codes to recognize items and provide real-time feedback to customers or operators, allowing for pre-transaction processing and automatic tallying of recognized items, with human assistance to improve accuracy and efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual scanning of items is used at checkout, then object identification can be achieved, but processing time increases and physical stress on operators increases
Solution Approach 1:
The machine vision system captures images of objects on the conveyor belt before they reach the scanning position, performing identification in advance. This preliminary action allows the system to process multiple objects simultaneously rather than sequentially, reducing overall processing time while maintaining identification accuracy
Solution Approach 2:
The patent replaces the manual mechanical scanning process with an automated machine vision system using cameras and image processing algorithms. This substitution eliminates the need for operators to physically handle and orient each object, reducing both processing time and physical stress on operators
2Extent of automation
If tunnel-based scanning systems are used, then automated processing is achieved, but the physical size limits what objects can be processed
Solution Approach 1:
Instead of using a tunnel structure that constrains objects in three-dimensional space, the patent uses an overhead camera system that captures images from above. This dimensional change allows objects of various sizes and shapes to be processed on an open conveyor belt surface, greatly increasing adaptability while maintaining automation
Solution Approach 2:
The patent extracts the scanning function from a confined tunnel structure and places it in an open environment above the conveyor belt. This extraction removes the physical size limitations imposed by tunnel walls, allowing the system to accommodate diverse object dimensions while preserving automated processing capabilities
3Productivity
If machine recognition systems are used, then processing speed increases, but complex and expensive equipment is required
Solution Approach 1:
The machine vision system is designed to automatically capture images, process them through recognition algorithms, and integrate with the POS system without requiring additional complex auxiliary equipment. The system serves itself by using standard cameras and software-based image processing, eliminating the need for specialized expensive hardware while maintaining high processing speed
4Measurement precision
If item-by-item processing is used, then each object can be thoroughly scanned, but overall throughput decreases
Solution Approach 1:
The machine vision system continuously captures images of multiple objects on the conveyor belt simultaneously rather than processing them one at a time. This continuous parallel processing maintains thorough scanning accuracy for each object while significantly increasing overall throughput by eliminating the sequential bottleneck
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 reduces processing time, minimizes physical stress, and allows for parallel processing of multiple items, enhancing checkout efficiency and reducing the risk of repetitive motion injuries while being compatible with existing systems.
Implementation Method 1
The machine vision system captures images of products, or other objects
Data Source
AI summary
An system and method for tallying objects presented for purchase preferably images the objects with a machine vision system while the objects are still, or substantially still. Images of the objects may be used to recognize the objects and to collect information about each object, such as the price. A pre-tally list may be generated and displayed to a customer showing the customer the cost of the recognized objects. A prompt on a customer display may be given to urge a customer to re-orient unrecognized objects to assist the machine vision system with recognizing such unrecognized objects. A tallying event, such as removing a recognized object from the machine vision system's field of view, preferably automatically tallies recognized objects so it is not necessary for a cashier to scan or otherwise input object information into a point of sale system.