Sample Tube Top Circle Edge Mapping for Reliable Robot Handling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing image-based detection methods in automated diagnostic analysis systems often erroneously detect stronger edge responses from objects other than the tops of sample tubes, such as barcode tags and tray components, which can adversely affect sample handling and processing.
Innovation Solution
The implementation of a convolutional neural network-based system that captures images of sample tube tops, intensifies the edges of the tubes while suppressing edges from other objects, and controls a robot for accurate handling based on the generated edge map.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If existing image-based detection methods are used to detect sample tube tops, then the detection process is simple and fast, but the system erroneously detects stronger edge responses from other objects (barcode tags, tray components) instead of tube tops
Solution Approach 1:
The patent changes the parameters of the detection system by introducing a convolutional neural network with multiple layers (convolutional layers, pooling layers, fully connected layers) that transforms the input image through successive transformations. This enables the system to learn complex patterns and distinguish tube tops from other objects based on hierarchical feature extraction, thereby improving detection accuracy while managing system complexity through structured architecture design.
Solution Approach 2:
The patent introduces an intermediary edge map generation step between image capture and final detection. The convolutional neural network first generates an edge map that highlights relevant edges while suppressing irrelevant ones, serving as an intermediary representation that facilitates more accurate tube top detection by separating signal from noise before the final detection stage.
2Reliability
If traditional edge detection is used, then the processing is computationally efficient, but the system provides stronger edge response to wrong objects like barcode tags and tray springs
Solution Approach 1:
The patent transforms the detection algorithm from traditional edge detection to a deep learning-based convolutional neural network approach. This parameter change in the algorithmic paradigm enables the system to learn discriminative features that reliably distinguish tube tops from other objects, improving detection reliability despite increased algorithmic complexity through the structured multi-layer architecture.
Solution Approach 2:
The patent segments the detection task into multiple hierarchical stages within the convolutional neural network: initial edge detection, feature extraction through convolutional layers, spatial downsampling through pooling layers, and final classification through fully connected layers. This segmentation of the detection process into specialized sub-tasks improves reliability by addressing different aspects of the detection problem at each stage.
3Measurement precision
If a convolutional neural network is implemented to enhance tube top edges and suppress other edges, then detection accuracy improves, but computational complexity and processing time increase
Solution Approach 1:
The patent performs preliminary edge enhancement and feature extraction through the convolutional neural network before the final detection decision is made. By pre-processing the image to generate an enhanced edge map that emphasizes tube top edges and suppresses other edges, the system reduces the computational burden on subsequent detection stages, thereby mitigating processing time increases despite the initial computational cost of the neural network.
Solution Approach 2:
The patent extracts and emphasizes only the relevant tube top edges from the input image through the convolutional neural network's selective feature extraction capability. By taking out and enhancing only the critical edge information while suppressing irrelevant edges from other objects, the system improves detection precision while reducing the amount of data that needs to be processed in subsequent stages, thereby managing processing time.
Data Source
Figure 1A~1B
Figure 2
Figure 3
AI summary
Methods for image-based detection of the tops of sample tubes used in an automated diagnostic analysis system may be based on a convolutional neural network to pre-process images of the sample tube tops to intensify the tube top circle edges while suppressing the edge response from other objects that may appear in the image. Edge maps generated by the methods may be used for various image-based sample tube analyses, categorizations, and/or characterizations of the sample tubes to control a robot in relationship to the sample tubes. Image processing and control apparatus configured to carry out the methods are also described, as are other aspects.