Blur Detection via Frequency Data Exclusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In building inspections, achieving high-resolution images that are free from blur is crucial for detecting fine abnormalities, but existing methods struggle to accurately determine image quality and identify the need for re-capture.
Innovation Solution
An information processing method that converts captured images into frequency characteristic data, generates secondary data by excluding predetermined areas, and determines image blur based on this secondary data, with the predetermined areas determined statistically from the first frequency characteristic data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the entire captured image is used for quality assessment, then the assessment covers all areas, but areas with abnormal luminance or outliers skew the blur determination accuracy
Solution Approach 1:
The patent extracts and removes abnormal luminance areas and outlier areas from the frequency characteristic data before performing blur determination. By taking out these irrelevant areas that would skew the assessment, the system achieves more accurate blur detection in the remaining valid image areas.
Solution Approach 2:
The patent applies different processing to different areas of the image based on their local characteristics. Areas with abnormal luminance or statistical outliers are identified and handled differently (excluded from analysis) compared to normal areas, allowing the blur determination to focus on regions with representative quality characteristics.
2Extent of automation
If statistical determination is used to identify predetermined areas, then the method is automated and objective, but the complexity of the processing increases
Solution Approach 1:
The system uses the image data itself to automatically identify and determine which areas should be excluded. By calculating frequency characteristics and statistics from the captured image, the system self-determines the predetermined areas without requiring external intervention or complex pre-configured rules.
Solution Approach 2:
The patent transforms the image data into frequency characteristic data and uses statistical parameters (mean, standard deviation) to identify abnormal areas. This parameter transformation enables automated, objective determination of areas to exclude based on quantitative criteria rather than complex logical rules.
Data Source
AI summary
An information processing method includes a conversion step of converting a captured image into first frequency characteristic data, a generation step of generating second frequency characteristic data by excluding data of a predetermined area from the first frequency characteristic data, and a determination step of determining whether or not the captured image is blurred based on the second frequency characteristic data. In the generation step, the predetermined area is determined according to whether or not the predetermined area falls within a predetermined range based on a statistic obtained based on the first frequency characteristic data.