Substrate Image Processing Region Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The miniaturization of substrates and components has made it difficult to recognize target objects for super-resolution processing, leading to inefficient image processing as the entire image region is often used, resulting in longer processing times and reduced efficiency.
Innovation Solution
A substrate working device that performs leading-substrate processing to detect and memorize region information for a specified detection target, allowing subsequent substrates to have a partial processing region set based on this information, thereby performing image processing only on the necessary area.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the entire image region is used as a processing region for super-resolution processing, then the target object can be detected with high accuracy, but the processing time becomes longer and efficiency is reduced
Solution Approach 1:
The patent divides the substrate into multiple regions (first region and second region) and applies different processing strategies to each region. The first region containing the detection target undergoes super-resolution processing, while the second region uses a different approach, thereby reducing overall processing time while maintaining detection accuracy.
Solution Approach 2:
The patent applies different image processing methods to different regions of the substrate based on their specific requirements. The first region receives super-resolution processing to ensure accurate detection of the target object, while the second region receives alternative processing, optimizing both accuracy and efficiency locally.
2Manufacturing precision
If super-resolution processing is performed on the entire image, then high-resolution data is obtained, but the processing complexity and time increase significantly
Solution Approach 1:
The patent segments the image processing into different regions with different resolution requirements. Only the first region containing the detection target undergoes complex super-resolution processing, while the second region uses simpler processing methods, reducing overall computational complexity.
Solution Approach 2:
The patent applies super-resolution processing only partially to the region containing the detection target rather than to the entire image. This partial action approach maintains the necessary high resolution for accurate detection while avoiding the excessive processing complexity and time that would result from processing the entire image.
Data Source
Figure 1
Figure 2~3
Figure 4
AI summary
A substrate working device including: an imaging device configured to image a substrate; a memory device configured to memorize various information; and an image processing device configured to perform, when specified work is performed with respect to multiple substrates, for a leading substrate, leading-substrate processing of performing imaging processing for detecting a specified detection target required for the specified work with respect to a leading image obtained by imaging the leading substrate using the imaging device, acquiring region information related to a region in the leading image in which the detection target was detected, and memorizing the region information in the memory device, and, for subsequent substrates except for the leading substrate, subsequent-substrate processing of setting a partial processing region in a subsequent image of the subsequent substrate captured by the imaging device based on the region information, and performing the image processing with respect to the set processing region.