Stranded Wire Image Segmentation for Precise Abnormality Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for detecting abnormalities in stranded wires using mean luminance values of images suffer from low accuracy, particularly when dealing with noisy or partially damaged wires.
Innovation Solution
An information processing device that acquires and divides images of stranded wires, calculates similarity levels using template matching, normalizes these levels, determines class classification thresholds, and identifies abnormalities based on inter-class distances exceeding a predetermined threshold.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If mean luminance value method is used for abnormality detection, then the detection process is simple, but the detection accuracy is low
Solution Approach 1:
The patent divides the image of the stranded wire into multiple divided images and performs template matching on each segment. This segmentation approach allows the system to capture local variations and abnormalities that would be missed by a global mean luminance calculation, thereby improving detection accuracy while maintaining computational efficiency through localized processing.
Solution Approach 2:
The patent replaces the simple mean luminance calculation method with template matching technology. This substitution introduces a more sophisticated image analysis mechanism that compares target images against reference templates, enabling accurate detection of abnormalities such as noise, small defects, and structural variations that luminance-based methods cannot reliably identify.
2Measurement precision
If template matching with multiple similarity levels is implemented, then abnormality detection accuracy is improved, but calculation complexity increases
Solution Approach 1:
The patent calculates similarity levels for multiple divided images and compares them against threshold values, performing calculations on a partial basis rather than requiring exhaustive analysis of the entire image at once. This approach achieves high detection accuracy by focusing computational resources on critical local regions while avoiding the need for overly complex global analysis.
Solution Approach 2:
The patent transforms the image data into similarity level parameters through template matching, then normalizes these parameters and compares them against threshold values. This parameter transformation simplifies the complexity by converting complex image data into comparable numerical values, making the detection process more manageable while maintaining high accuracy through multi-level similarity assessment.
3Measurement precision
If image division and multiple similarity calculations are performed, then detection precision is improved, but processing time increases
Solution Approach 1:
By dividing the image into multiple segments and performing template matching on each segment independently, the patent achieves high detection precision through localized analysis. This segmentation strategy actually reduces processing time compared to analyzing the entire image at once, as parallel processing of smaller segments is more efficient and allows for faster identification of abnormalities in specific regions.
Solution Approach 2:
The patent applies different processing approaches to different parts of the image based on local characteristics. By focusing template matching on specific divided regions rather than uniformly processing the entire image, the system achieves high precision where needed while reducing unnecessary computations in normal areas, thereby optimizing the balance between detection precision and processing time.
Data Source
AI summary
An information processing device includes an acquisition unit that acquires an image of a stranded wire, a division unit that divides the image of the stranded wire, a calculation unit that calculates a plurality of similarity levels by using a plurality of object images set out of a plurality of images obtained by the division and a plurality of comparative images set out of the plurality of images, normalizes the plurality of similarity levels, calculates a class classification threshold value by using a plurality of values obtained by the normalization, calculates one value in regard to each class based on the class classification threshold value, and calculates a difference between the calculated two values as an inter-class distance, and a determination unit that determines that the stranded wire is abnormal when the inter-class distance is greater than or equal to a predetermined first threshold value.