Unified Interface for Rule-Based and Machine Learning Image Processing Tools
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current image processing systems require significant time and effort for users to set up both rule-based and machine learning tools on separate interfaces, lacking a common interface for efficient operation.
Innovation Solution
An image processing device with a UI generation unit to create a common user interface for setting both machine learning and rule-based tools, allowing them to share a data set and execute image processing sequentially, with the rule-based tool performing initial corrections before machine learning processing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If separate interfaces are used for rule-based tool and machine learning tool, then each tool can be configured independently, but user effort and time for setting up both tools increases
Solution Approach 1:
The patent merges the configuration interfaces for rule-based tools and machine learning tools into a single unified interface. This allows users to configure both tool types simultaneously without switching between separate interfaces, directly reducing setup time while maintaining the ability to independently configure each tool's parameters through the common interface.
Solution Approach 2:
The unified interface is designed to be universal, supporting both rule-based tool configuration and machine learning tool configuration through the same interface structure. This multi-functional interface eliminates the need for separate specialized interfaces, reducing user effort while preserving tool-specific configuration capabilities.
2Ease of manufacture
If separate interfaces are used for rule-based tool and machine learning tool, then each tool has dedicated settings, but overall system operation becomes more complex
Solution Approach 1:
By combining multiple tool configurations into a single interface structure, the system reduces operational complexity while maintaining ease of use. The unified interface presents a consistent, predictable structure for configuration, eliminating the cognitive load of switching between different interface paradigms.
Solution Approach 2:
Within the unified interface, the system segments configuration options into distinct sections for rule-based tools and machine learning tools. This segmentation maintains organization and simplicity for users while achieving the overall goal of interface unification, making the system easier to operate despite the combined functionality.
3Measurement precision
If machine learning tool requires multiple images for training, then processing accuracy can be improved, but data preparation time increases
Solution Approach 1:
The system performs preliminary actions by automatically organizing and preparing training images within the unified interface before machine learning processing begins. The interface provides pre-configured options for image selection, organization, and preparation, reducing the manual time required while ensuring adequate training data for accurate processing.
Solution Approach 2:
The unified interface incorporates self-service features that automatically handle image data preparation, organization, and validation. The system can autonomously manage the complex tasks of preparing multiple training images, reducing user effort and time while maintaining the data quality needed for accurate machine learning processing.
Data Source
AI summary
The present disclosure is to allow both a rule-based tool and a machine learning tool to be set on a common interface, thereby reducing the time and effort of the user. An image processing device 1: generates a user interface screen for displaying a setting window; receives an input for arranging a machine learning tool and a rule-based tool in the setting window of the user interface screen, and an input of a common data set including a plurality of images to be referred to by the machine learning tool and the rule-based tool; and executes one of the image processing by the machine learning tool or the image processing by the rule-based tool on the data set, and executes the other image processing on the data set after the one image processing is executed.