Image Inspection ROI Adjustment for Out-of-View Objects
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing image inspection devices struggle to accurately determine the non-defectiveness of objects when the inspection target region is out of the capturing field of view, and adjusting the region of interest (ROI) is difficult without suitable visual characteristics.
Innovation Solution
An image inspection device that uses a machine learning model with feature extraction sections to automatically adjust the ROI based on reference positions and angles, allowing for object detection without manual ROI setting.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If the ROI position and angle are fixed with respect to the capturing field of view, then the device complexity is reduced, but the inspection capability deteriorates when the object is out of the ROI
Solution Approach 1:
The patent applies dynamics by making the ROI position and angle adjustable rather than fixed. The inspection setting section dynamically adjusts the ROI based on the detected object's position and angle in the captured image, allowing the system to adapt to different object locations while maintaining reliable inspection capability.
2Reliability
If the position correction tool is used to adjust the ROI, then the inspection capability for out-of-ROI objects is improved, but the ease of operation deteriorates when no suitable visual characteristic is available
Solution Approach 1:
The patent applies self-service by having the system automatically adjust the ROI based on the detected object's position and angle without requiring user intervention. The inspection setting section autonomously determines the appropriate ROI configuration, eliminating the need for users to manually set reference positions or angles, thereby maintaining ease of operation while improving inspection capability.
3Adaptability or versatility
If manual ROI setting is required, then the adaptability to different objects is improved, but the loss of time increases due to user setup time
Solution Approach 1:
The patent applies preliminary action by pre-configuring the system with the machine learning model and feature extraction sections that enable automatic ROI adjustment. Once the system is initialized, it automatically adapts to different objects without requiring manual setup, thereby reducing time loss while maintaining high adaptability to various object types and positions.
Data Source
AI summary
An inspection device extracts, from a learning image, a first feature amount that reflects an angle of a window and a position specified by the window, and a second feature amount corresponding to a position specified by the window. The inspection execution section extracts a third feature map from the captured image, determines a candidate region based on the third feature map and the first feature amount, extracts a fourth feature map from the captured image, and makes a classification based on the fourth feature map, the candidate region, and the second feature amount, and outputs the inspection result in which the candidate region is set as a detection region of the object in a case where a fourth feature amount corresponding to the candidate region is classified as belonging to the same class as the second feature amount.