Boundary Detection in Culture Medium Wells Using Edge Shift Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing image processing techniques fail to accurately specify the boundary between a valid area and an invalid area in the peripheral edge of a recess in images of culture medium-containing containers due to issues like concave meniscus formation, tapered well sides, and air bubbles, leading to unclear or multiple edge features.
Innovation Solution
An image processing method involving the setting of multiple search areas along the peripheral edge, edge detection, and relative shift analysis to determine the boundary position based on edge positions, intensities, and similarity between adjacent search areas, even in cases of unclear edges.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional edge detection methods are used to identify the boundary between valid and invalid areas, then the processing is simple and fast, but the boundary detection becomes inaccurate due to meniscus formation, tapered well sides, reflections, shadows, and air bubbles
Solution Approach 1:
The image is divided into multiple search areas arranged along the peripheral edge of the well. Each search area is processed independently to detect local edge features, and the results are integrated to determine the overall boundary. This segmentation allows the system to handle local variations (meniscus, reflections, shadows) by focusing on relevant local patterns rather than applying a single global detection method.
Solution Approach 2:
A template pattern representing the expected boundary feature is introduced as an intermediary. The template is correlated with image patterns in each search area to identify matching boundary locations. This template acts as a mediator that guides the detection process, enabling accurate boundary identification even when direct edge detection fails due to meniscus formation, tapered sides, or lighting artifacts.
2Reliability
If multiple image processing techniques are combined to improve boundary detection accuracy, then the detection reliability increases, but the processing time and computational load increase
Solution Approach 1:
By dividing the image into multiple search areas, the system can apply template correlation and edge detection independently to each area. This segmentation enables parallel processing of different regions, reducing overall processing time while maintaining high reliability through comprehensive coverage of the peripheral edge.
Solution Approach 2:
The system applies processing only to search areas located at the peripheral edge of the well, rather than processing the entire image. This partial action approach focuses computational resources on the critical boundary regions where boundary detection is needed, while ignoring areas that do not contain boundary information, thus reducing total processing time.
Data Source
AI summary
An image processing method that includes setting a plurality of search areas of a predetermined size having mutually different circumferential positions along a peripheral edge part and extending in a radial direction from a center of a recess toward the peripheral edge part near the peripheral edge part in an image, executing an edge detection in each search area to obtain detected edge position and edge intensity for each search area, obtaining a relative shift amount for making a degree of similarity of image patterns highest for each search area when another search area adjacent to the search area in the circumferential direction is shifted in the radial direction with respect to the search area, and specifying a position of the boundary in one search area based on the edge positions, the edge intensities and the relative shift amounts in the search area and each of the search areas in neighboring ranges in the circumferential direction.