Merchandise Recognition Dictionary Update via Hand Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing point-of-sale systems face challenges in generating high-quality image dictionaries for merchandise recognition, as images with hands interfere with the process, requiring users to exert extra effort to avoid hand inclusion, which is burdensome.
Innovation Solution
A system that automatically processes images from a product scanner, determines if a hand is present, and only updates the dictionary if no hand is detected, allowing for efficient generation and updating of image recognition models without user intervention.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If the user takes additional time and effort to avoid acquisition of images with a hand depicted therein, then the quality of the image dictionary improves, but the ease of operation deteriorates
Solution Approach 1:
The system performs self-service by automatically detecting hands in images and excluding them from the dictionary without requiring user intervention. The control unit autonomously processes images, identifies hand presence, and filters out inappropriate images, eliminating the need for users to manually avoid hand inclusion while maintaining dictionary quality.
Solution Approach 2:
The system implements feedback by continuously monitoring image quality through hand detection and automatically adjusting the dictionary generation process. When a hand is detected in an image, the system provides feedback by excluding that image from the dictionary, creating a closed-loop system that maintains quality without user effort.
2Ease of operation
If automatic hand detection and filtering is implemented, then the ease of operation improves, but the device complexity increases
Solution Approach 1:
The control unit performs multiple functions within a single integrated system: it processes images from the product scanner, detects hand presence using recognition technology, determines merchandise information, and filters images for dictionary generation. This multi-functionality consolidates what would otherwise require separate systems into one unified device, managing complexity through integration rather than multiplication of components.
Data Source
AI summary
According to one embodiment, a merchandise information processing device includes a control unit and a communication interface connectable to a product scanner. The control unit receives an image from the product scanner. The image is obtained when a user holds a merchandise item in front of an image pickup unit of the product scanner in a scanning operation. The control unit processes the image to obtain a merchandise code for the merchandise item in the image by object recognition and may also process the image to determine if a hand of the user appears in the image. The control unit saves the image to update a dictionary file only if the merchandise code obtained by the object recognition does not match a merchandise code received from the product scanner in association with the image and the hand of the user is determined not to be in the image.