Vision-Based Syringe Level Measurement With OCR Error Correction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Mechanical methods of measuring liquid level in containers with linear scales suffer from wear and tear, leading to increased inaccuracy over time, and existing vision-based methods lack precision in identifying liquid level indicators.
Innovation Solution
A computer vision-based system employing image processing, machine learning, and optical character recognition to accurately measure liquid levels in containers by extracting features, identifying liquid level indicators, and correcting misread values, using techniques such as color-based image segmentation, contour detection, and regression-based straight line fitting.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If mechanical methods are used for measuring liquid level, then physical coupling and geared coupling are achieved, but wear and tear of parts leads to increased inaccuracy over time
Solution Approach 1:
The patent replaces mechanical feedback mechanisms with a vision-based measurement system that uses image processing and machine learning algorithms to detect liquid levels. The system captures images of the container with liquid level indicators, processes these images computationally to identify the liquid level position on the scale, and determines volume without any mechanical contact or moving parts, thereby eliminating wear and tear issues
Solution Approach 2:
The system creates an optical copy of the liquid level indicator and scale markings through image capture. By processing this visual copy digitally rather than using physical mechanical components, the system achieves measurement functionality without the wear and tear that plagues mechanical systems
2Measurement precision
If existing vision-based methods are used for liquid level measurement, then non-contact measurement is achieved, but precision in identifying liquid level indicators is insufficient
Solution Approach 1:
The system performs preliminary segmentation of the image to isolate the container, liquid level indicator, and scale markings before measurement. By pre-processing the image to extract only relevant features and remove background interference, the system simplifies subsequent analysis and improves detection precision without requiring overly complex real-time processing
Solution Approach 2:
The system employs machine learning models that are trained on labeled data of liquid level images, enabling them to learn and improve at identifying liquid level indicators and scale markings. The feedback mechanism allows the system to continuously refine its detection accuracy by comparing predictions with actual measurements and adjusting parameters accordingly
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Conventionally, mechanical methods of measuring linear position over a scale required physical coupling with system(s), such as potentiometer-based feedback etc. Such kinds of mechanical feedback mechanisms need geared coupling. And along with a mechanical system comes problems of wear and tear of parts which can lead to increased inaccuracy of the setup over time. With increased capabilities of computer vision-based techniques, a non-contact image-based measurement of linear position has become of prime importance. Embodiments of the present disclosure provide system and method that implement direct visual measurement of liquid level inside a linear measurement setup (syringe here) by employing various techniques such as computer vision, machine learning techniques, and the like, wherein various features are extracted that in turn allow to have a measurement of a liquid level identified or indicator (plug/meniscus) position in a syringe/container.