Image Defect Detection with Histogram-Adjusted Neural Sub-Regions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for detecting defects in product images, such as misprinted characters, are often inaccurate.
Innovation Solution
A method involving geometric correction using SIFT and RANSAC algorithms, histogram equalization, and neural network training to enhance image sub-regions for accurate defect detection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional defect detection methods are used, then the detection process is simple, but the detection accuracy is poor
Solution Approach 1:
The patent divides the image into multiple sub-regions after geometric correction and processes each sub-region independently through histogram equalization and neural network analysis. This segmentation allows the system to handle complex images by breaking them into manageable portions, improving detection accuracy without overwhelming the processing system.
Solution Approach 2:
The patent performs geometric correction using SIFT and RANSAC algorithms before defect detection, and pre-processes images through histogram equalization. These preliminary actions enhance image quality and prepare the data for more accurate neural network analysis, resolving the contradiction by preparing complex data in advance rather than during real-time detection.
2Measurement precision
If image processing steps are added to improve quality, then defect detection accuracy improves, but processing time increases
Solution Approach 1:
By dividing the image into sub-regions and processing them in parallel, the patent reduces overall processing time. Each sub-region can be independently corrected and analyzed, allowing concurrent operations that complete faster than sequential processing of the entire image.
Solution Approach 2:
The patent applies histogram equalization to transform pixel intensity distributions, enhancing image contrast and feature visibility. This parameter transformation improves detection accuracy while the algorithmic optimization keeps processing time manageable by working with transformed data rather than original images.
Data Source
AI summary
An image detection obtains first images with defects. Each of the first images is corrected and divided to obtain first sub-region images. The first sub-region images are processed to obtain processed first sub-region images. The processed first sub-region images are used to train a neural network to obtain a target mode. Second images are obtained. Each of the second images is corrected and divided to obtain second sub-region images. The second sub-region images are processed to obtain processed second sub-region images. The target model is applied to detect each of the processed second sub-region images to obtain a detection result. The method can detect defects in images accurately and efficiently.