Object Recognition Apparatus Automatic Resumption
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In check-out systems, when an article of interest is not included in the reference articles displayed as candidates during object recognition, operators must manually cancel and re-capture the image, which is inefficient.
Innovation Solution
An information processing apparatus that automatically resumes object recognition processing by recalculating similarity degrees between newly captured images and stored reference objects if no candidate is selected within a predetermined time, allowing for continuous image capture and comparison.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If the system displays reference articles as candidates when object recognition fails to identify a captured article, then the operator can select from candidate articles, but the operator must manually cancel and re-capture if the intended article is not in the candidates
Solution Approach 1:
The system performs preliminary actions by automatically capturing a new image and resuming object recognition processing before the operator can manually cancel. When no candidate is selected within a predetermined time, the system proactively initiates the next recognition cycle, eliminating the need for manual cancellation and re-capture operations.
Solution Approach 2:
The system serves itself by automatically detecting when no candidate selection occurs within the time limit and autonomously initiating the next object recognition cycle. This self-service mechanism eliminates dependence on manual operator intervention to restart the recognition process after candidate display.
2Measurement precision
If the operator must manually cancel and re-capture images when the intended article is not in the candidate list, then recognition accuracy can be maintained, but operational efficiency decreases
Solution Approach 1:
The system maintains continuous useful action by automatically initiating the next object recognition cycle without interruption when no candidate is selected. This continuous operation eliminates idle time between recognition attempts while maintaining accuracy through the same rigorous comparison process, thereby improving operational efficiency without sacrificing recognition precision.
3Measurement precision
If the system waits for operator selection after displaying candidates, then accurate identification can be achieved, but the process becomes slower due to manual intervention requirements
Solution Approach 1:
The system performs preliminary preparation by having the next image capture and processing ready to execute immediately when the current candidate selection period expires. This preliminary preparation ensures that the transition to the next recognition cycle is seamless, maintaining identification accuracy while eliminating delays caused by manual intervention.
Data Source
AI summary
An object recognition apparatus includes an image capturing unit, a storage unit that stores feature data of a plurality of reference objects, a display unit, and a processor. The processor calculates degrees of similarity between an object in the captured image and a plurality of reference objects, based on the feature data of the reference objects, selects some of the reference objects as candidates objects based on the calculated degrees of similarity, and controls the display unit to display the candidate objects and a message to select one of the candidate objects. If no candidate object is selected within a predetermined time after the candidate objects and the message have been displayed, and thereafter a new image is captured by the image capturing unit, the processor removes the message and calculates degrees of similarity between an object in the newly captured image and the plurality of reference objects.