Commodity Recognition Using Operator Posture Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional commodity recognition apparatuses often incorrectly detect non-commodity objects, leading to unnecessary recognition processing and reduced efficiency in registration operations, as they lack effective means to differentiate between intended and unintended objects during imaging.
Innovation Solution
Incorporating a posture sensor to determine if the operator is in a suitable position before initiating commodity recognition processing, ensuring that only intended images of commodities are processed and displayed for selection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the commodity recognition apparatus executes recognition processing on any detected object, then the apparatus can identify commodity candidates, but it may process unintended objects (e.g., operator's body parts) leading to erroneous candidate displays and reduced operational efficiency
Solution Approach 1:
The patent introduces a posture sensor as an intermediary device that mediates between the image capture and recognition processing. The posture sensor detects the operator's body position and provides posture information that serves as a filtering criterion, allowing the system to distinguish between intentional commodity imaging and accidental body part capture before initiating recognition processing
Solution Approach 2:
The system performs preliminary posture detection and evaluation before executing commodity recognition processing. By checking whether the operator's posture satisfies predetermined conditions (indicating proper holding position) in advance, the system prevents unnecessary recognition processing on unintended objects, thereby improving operational efficiency while maintaining detection accuracy
2Loss of information
If the commodity recognition apparatus displays candidate commodities for operator selection, then the apparatus provides comprehensive recognition results, but it requires additional operator intervention to clear erroneous candidates, increasing operation time
Solution Approach 1:
The system performs preliminary validation of the imaging conditions through posture detection before generating recognition results. By ensuring that only images taken when the operator is in the correct posture (holding the commodity properly) are processed, the system prevents erroneous candidate generation in the first place, eliminating the need for operator correction and reducing time loss
Data Source
AI summary
According to an embodiment, a commodity recognition apparatus includes a first camera configured to image a commodity, a posture sensor configured to acquire information indicating a posture of an operator, and a processor configured to acquire the image of the commodity from the first camera, execute commodity recognition processing on the image of the commodity to identify possible matches to previously registered commodity identities upon determining that the posture of the operator satisfies a specified condition according to information from the posture sensor, cause a plurality of commodity candidates are identified as possible matches in the commodity recognition processing, to be displayed on a display screen, and wait for an operator selection of one commodity candidate from the plurality of commodity candidates displayed on the display screen.