Automated Object Region Inspection Condition Mapping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The burden on operators is significant when determining the correspondence between object regions and inspection conditions for captured images, especially when multiple objects with varying inspection criteria are present, as they need to manually specify coordinates and types for each object region.
Innovation Solution
A computer-readable storage medium and apparatus that uses a trained object detection model to automatically detect object regions and generate correspondence data, specifying object region information and associated inspection conditions, thereby reducing operator burden and improving efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual determination of correspondence between object regions and inspection conditions is performed, then inspection accuracy can be ensured, but operator burden increases significantly
Solution Approach 1:
The system enables automated self-service by having the inspection apparatus automatically determine correspondence data between object regions and inspection conditions using machine learning models, eliminating the need for manual operator intervention while maintaining inspection accuracy
Solution Approach 2:
The manual mechanical process of determining correspondence is replaced with an automated information processing system using trained machine learning models that automatically analyze captured images and generate correspondence data without human operators
2Ease of operation
If automated object detection is used, then operator burden is reduced, but complexity of the inspection system increases
Solution Approach 1:
The machine learning model serves multiple functions simultaneously - it detects object regions, determines object types, and establishes correspondence with inspection conditions, consolidating what would otherwise require separate processing steps into a single universal component
Solution Approach 2:
The trained machine learning model acts as an intermediary between the captured image and the inspection system, automatically translating visual data into structured correspondence data that the inspection apparatus can process, thereby simplifying the overall system architecture
3Measurement precision
If multiple inspection conditions are applied to different objects, then inspection precision improves, but data generation burden increases
Solution Approach 1:
The system performs preliminary action by pre-training machine learning models with inspection condition data before actual inspection, enabling the model to automatically determine appropriate correspondence data during inspection without requiring time-consuming manual setup for each object
Data Source
AI summary
Based on first captured image data indicating a first captured image of a first inspection target, K object regions corresponding to K (K is an integer larger than or equal to one) objects are detected by using a trained object detection model. The first inspection target includes the K objects and has no abnormality in visual. First correspondence data indicating K correspondences corresponding to respective ones of the K object regions is generated. Each of the K correspondences indicates a correspondence between object region information and condition information. The object region information is information specifying an object region in the first captured image. The condition information indicates an inspection condition associated with a type of the object region, among L (L is an integer larger than or equal to one and smaller than or equal to K) inspection conditions. The first correspondence data is stored in a memory.