Minute Target Detection Through Noise Region Exclusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing image processing algorithms struggle to accurately distinguish between minute detection targets and noise in captured images, particularly in the presence of high-density regions or poor image quality, leading to reduced detection accuracy and instability.
Innovation Solution
A detection system that includes a candidate generator, a pre-processor, and a detector to identify and exclude noise regions, using machine learning models and pre-processing techniques to enhance the detection of minute targets by focusing on structural features and density factors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If image processing algorithms such as particle analysis are used to detect minute targets, then detection capability is provided, but the algorithms cannot distinguish between minute particulate detection targets and noise, leading to reduced accuracy
Solution Approach 1:
The detection system segments the detection process into multiple specialized components: a candidate generator that identifies potential targets, a pre-processor that divides images into small regions and evaluates them, and a detector that performs final classification. This segmentation allows each component to specialize in specific tasks, improving overall detection accuracy while managing complexity through modular design.
Solution Approach 2:
The pre-processor acts as an intermediary between the candidate generator and the detector. It divides the captured image into small regions, evaluates each region for features of subjects other than detection targets, and generates exclusion regions. This intermediary processing step filters out noisy areas before final detection, improving accuracy without requiring the detector to handle all complexity alone.
2Productivity
If detection is performed in high-density regions, then more detection targets may be found, but visibility of minute shapes is reduced by other subjects, inhibiting detection and reducing stability
Solution Approach 1:
The system applies different processing strategies to different regions of the image. The pre-processor divides the image into small regions and evaluates each region's characteristics, identifying areas with features of subjects other than detection targets. Exclusion regions are generated for areas where detection reliability would be poor, allowing the system to focus detection resources on high-quality regions while maintaining overall productivity.
3Measurement precision
If conventional image processing is used, then processing speed is maintained, but accuracy of distinguishing detection targets from noise is reduced
Solution Approach 1:
The pre-processor performs preliminary evaluation of image regions before the final detection step. By dividing the image into small regions and identifying exclusion regions in advance, the system prepares the data structure and filters out obvious noise areas before the detector performs its classification. This preliminary action reduces the computational burden on the detector and improves overall processing efficiency.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A detection system includes: a candidate generator; a pre-processor; and a detector. The candidate generator generates candidates for a detection target image, in which a detection target is captured, from a captured image for detection that includes an image of an object having the detection target and a noise image. The pre-processor that divides the captured image for detection into small regions and determines whether or not each small region image has features of subjects other than the object having the detection target based on an image feature amount of the small region image to obtain an exclusion region in the captured image based on a determination result. The detector detects the detection target image from among the candidates for the detection target image that are not included in the exclusion region by predetermined detection processing.