Adaptive Edge Size Reduction in Image Pyramid Pattern Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The coarse-to-fine search method in image processing faces challenges in selecting appropriate size reduction factors for edges, leading to unstable edge detection due to environmental influences and reduced processing speed when edges with varying sharpness are considered.
Innovation Solution
An image processing method that generates a model pyramid with different layers having unique size reduction factors based on the maximum size reduction factors calculated for individual edges, ensuring that only edges with sufficient size reduction factors are used as model edges, preventing unstable edge generation and enabling high-speed, robust, and accurate pattern matching.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If size reduction is performed without taking edge size into consideration, then processing speed is improved, but edge stability deteriorates due to blurring
Solution Approach 1:
The patent applies local quality by setting different size reduction factors for different edges based on their individual sizes. Small edges use smaller size reduction factors to maintain stability, while large edges can tolerate larger size reduction factors for faster processing. This localized adaptation resolves the contradiction between processing speed and edge stability.
Solution Approach 2:
The patent introduces dynamics by making the size reduction factor variable rather than fixed. The size reduction factor is dynamically determined based on the size of each edge, allowing the system to adapt the degree of size reduction to the specific characteristics of each edge, thereby balancing processing speed and stability.
2Productivity
If a large size reduction factor is set, then processing speed is improved, but detection accuracy deteriorates due to edge blurring
Solution Approach 1:
The patent applies local quality by determining size reduction factors individually for each edge based on its size. This allows small edges to maintain higher detection accuracy with smaller size reduction factors, while large edges can use larger size reduction factors for faster processing without sacrificing overall detection accuracy.
Solution Approach 2:
The patent changes the parameter of size reduction factor from a fixed value to a variable that depends on edge size. This parameter change enables the system to optimize both processing speed and detection accuracy by adjusting the size reduction factor according to the specific characteristics of each edge.
3Reliability
If a small size reduction factor is set, then edge stability is improved, but processing speed deteriorates
Solution Approach 1:
The patent applies local quality by assigning different size reduction factors to different edges based on their sizes. Small edges receive smaller size reduction factors to maintain stability, while large edges receive larger size reduction factors to improve processing speed, thus resolving the contradiction between stability and speed.
Solution Approach 2:
The patent introduces dynamics by making the size reduction factor adaptive rather than static. The system dynamically selects appropriate size reduction factors based on edge size characteristics, allowing it to optimize the balance between edge stability and processing speed for different types of edges.
4Device complexity
If size reduction is performed on all edges uniformly, then processing simplicity is maintained, but detection reliability deteriorates due to unstable small edges
Solution Approach 1:
The patent applies local quality by differentiating the size reduction treatment for different edges based on their sizes. Instead of uniform size reduction, each edge receives a size reduction factor appropriate to its size, which improves detection reliability while adding manageable complexity to the processing system.
Solution Approach 2:
The patent applies segmentation by dividing edges into different categories based on their sizes and applying different size reduction factors to each category. This segmentation approach improves detection reliability by treating small and large edges differently, while keeping the overall processing framework organized and manageable.
Data Source
AI summary
A processor performs pattern matching on a search target image using a reference image. The processor uses the reference image to calculate a model pyramid, which has model edges and different layers, and uses the search target image to calculate the search target pyramid, which has search target edges and layers having size reduction factors which are the same as those of the model pyramid. The processor performs pattern matching on the search target pyramid using the model pyramid. Calculation of the model pyramid includes (i) extracting and calculating sizes of edges from the reference image, (ii) obtaining maximum size reduction factors of the individual edges, and (iii) setting an edge (a) which has a size reduction factor equal to or larger than a target layer size reduction factor and (b) which has been subjected to size reduction as a model edge of the target layer.