Multi-Focus Imaging Learning to Reduce Unnecessary Captures
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing image capturing methods struggle with insufficient depth of field, requiring numerous images for depth composition, which increases processing load and is inconvenient for inexperienced photographers.
Innovation Solution
A learning apparatus that utilizes machine learning to determine optimal imaging settings for depth composition, using professional images as teacher data to guide inexperienced users in capturing high-resolution composite images.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the number of captured images is increased to improve composite image resolution, then the perceived resolution is improved, but the processing load increases
Solution Approach 1:
The patent changes the parameter of image selection from capturing many images to selectively capturing only necessary images based on focus evaluation. The system evaluates focus quality metrics and uses this information to determine which images are needed for the composite, thereby reducing the total number of images while maintaining resolution quality.
2Measurement precision
If inexperienced photographers manually adjust imaging settings through trials and errors, then they can eventually obtain optimum settings, but the time and complexity of operation increase
Solution Approach 1:
The system performs self-service by automatically evaluating focus quality and determining optimal imaging settings without requiring user intervention. The camera autonomously analyzes focus metrics, selects appropriate focus positions, and configures shooting parameters, eliminating the need for photographers to perform manual trials and errors.
Solution Approach 2:
The system implements feedback by evaluating focus quality metrics from captured images and using this information to adjust and optimize subsequent imaging settings. The focus evaluation results feed back into the control system, which automatically modifies shooting parameters to achieve optimal composite image quality without user intervention.
3Measurement precision
If the number of captured images is increased to ensure sufficient perceived resolution, then the composite image quality is improved, but the convenience of operation decreases
Solution Approach 1:
The system automates the entire process of focus evaluation and image selection, making it self-service. The camera independently determines which images are necessary for high-quality compositing based on focus metrics, eliminating the need for users to manually configure multiple shooting parameters or select images.
Solution Approach 2:
Instead of capturing a large fixed number of images, the system performs partial action by capturing only the specific number and types of images needed based on real-time focus evaluation. This avoids excessive image capture while still achieving sufficient composite image quality.
Data Source
Figure 1
Figure 2A~2D
Figure 3
AI summary
A learning apparatus includes a model generating unit configured to generate, by using teacher data including a subject and a composite image generated from a plurality of images captured based on settings predetermined for the subject, a model for generating imaging settings suitable for generating a composite image of the subject through machine learning. The plurality of images are images captured at in-focus positions different in an optical axis direction. The settings include at least the in-focus positions. The composite image is an image generated by extracting in-focus regions from the plurality of images.