Image Comparison Using Edge Morphology
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing image comparison methods that compare pixel values are inadequate when a user is interested in the appearance of objects and wants to ignore other differences between images.
Innovation Solution
An image comparison method that involves binarizing, edge detection using the Canny algorithm, morphological expansion, and performing OR and XOR operations on the edge images to improve accuracy and reduce errors caused by external factors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If pixel value comparison method is used, then the comparison process is simple, but the accuracy of object appearance comparison deteriorates
Solution Approach 1:
The patent segments the image comparison task into distinct stages: binarization to separate foreground objects from background, edge detection to isolate object boundaries, and morphological operations to refine object shapes. This segmentation allows the system to focus computational resources on object appearance features rather than processing every pixel, thereby improving accuracy while maintaining operational simplicity.
Solution Approach 2:
The patent extracts only the essential features needed for object appearance comparison by applying binarization and edge detection algorithms. These operations extract binary masks and edge information that represent object appearances, filtering out irrelevant pixel-level variations and external factors, thus achieving accurate object appearance comparison.
2Loss of time
If pixel value comparison method is used, then the processing time is short, but the reliability of image matching deteriorates
Solution Approach 1:
The patent applies preliminary processing steps including binarization and edge detection before the actual comparison. These preliminary actions prepare the images by extracting meaningful features and eliminating noise, which ensures that subsequent comparison operations are more reliable and require less computational time, thus improving reliability without significant time loss.
Solution Approach 2:
The patent changes the parameter representation from raw pixel values to binary values and edge information. This parameter transformation enables the system to compare object appearances more reliably by focusing on structural features rather than intensity values, reducing the impact of lighting variations and external factors while maintaining efficient processing speed.
3Device complexity
If simple pixel comparison is used, then the method is easy to implement, but it cannot ignore external factors affecting images
Solution Approach 1:
The patent introduces intermediary processing steps between the input images and the comparison operation. Binarization and edge detection act as intermediaries that transform the original images into processed representations that are less sensitive to external factors like lighting changes and background variations, allowing the system to ignore these harmful factors while maintaining easy implementation through standard image processing algorithms.
Data Source
AI summary
In an image comparison method, an original reference image and an original test image are obtained. The original reference image and the original test image are binarized to obtain a reference binary image and a test binary image. The reference binary image and the test binary image are detected edges to obtain a reference edge image and a test edge image. A morphological expansion is performed on the reference edge image to obtain an expanded reference edge image. An OR operation is performed on the extended reference edge image and the test edge image to obtain an extended test edge image. An XOR operation is performed on the expanded reference edge image and the expanded test edge image. The method improves the accuracy of image comparison.