Information Processing for Crack Width Measurement Amid Surface Irregularities
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for determining defect attributes in images, such as crack width in concrete structures, often inaccurately widen the measurement due to influences from chipping or surface irregularities, leading to incorrect assessments of defect severity.
Innovation Solution
An information processing device and method that detect defects and determine their attributes by extracting feature amounts from partial images, using a combination of defect detection, feature extraction, and attribute determination units, including thinning, polyline conversion, and multi-class classification to accurately measure crack width.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If the width of a crack is determined using luminance distribution data of a local region centered on pixels representing the crack, then the crack width can be determined automatically from image data, but the crack may be determined to be wider than it actually is due to surface irregularities such as chipping or bubbles
Solution Approach 1:
The invention extracts only the necessary feature amounts (luminance distribution characteristics) from the local region image data, separating the relevant crack information from irrelevant surface irregularities. By focusing extraction on specific luminance patterns rather than using the entire local region, the method isolates the crack width information while excluding distortions from chipping or bubbles.
Solution Approach 2:
The invention applies different analysis approaches to different parts of the image data. Instead of uniformly analyzing the entire local region, it identifies and analyzes only the portions containing crack pixels with specific luminance distribution characteristics, while ignoring areas affected by surface irregularities. This localized quality-based analysis improves measurement precision.
2Manufacturing precision
If the maximum crack width is calculated based on individual pixel crack width determinations using local region luminance distribution, then the maximum width can be identified, but the maximum value may be greater than it actually is due to influences from areas where the crack is determined to be wider than it actually is
Solution Approach 1:
The invention uses feedback mechanisms where the determination of crack width at each pixel is continuously refined based on the luminance distribution characteristics. The system compares the extracted feature amounts against reference data or thresholds and adjusts the determination accordingly, ensuring that outlier measurements caused by surface irregularities are corrected rather than propagated to the maximum width calculation.
Data Source
AI summary
There is provided with an information processing device. A defect detecting unit detects a defect of an object in an input image. An extracting unit extracts a feature amount pertaining to a partial image of the defect from the input image, on the basis of a result of detecting the defect. An attribute determining unit determines an attribute of the defect using the feature amount pertaining to the partial image of the defect.