Vision-based module for accurately reading linear scales in a laboratory

TL;DR

This paper presents a vision-based system that accurately reads measurements from linear scales in laboratory instruments, mimicking human reading capabilities for autonomous robotic applications.

Contribution

It introduces a novel approach combining image transformations and feature extraction to accurately read linear scales, improving robustness and efficiency over existing methods.

Findings

System achieves high accuracy in reading syringe and cylinder levels

Comparable results to human readings demonstrate effectiveness

Reduces processing to relevant image regions for efficiency

Abstract

Capabilities and the number of vision-based models are increasing rapidly. And these vision models are now able to do more tasks like object detection, image classification, instance segmentation etc. with great accuracy. But models which can take accurate quantitative measurements form an image, as a human can do by just looking at it, are rare. For a robot to work with complete autonomy in a Laboratory environment, it needs to have some basic skills like navigation, handling objects, preparing samples etc. to match human-like capabilities in an unstructured environment. Another important capability is to read measurements from instruments and apparatus. Here, we tried to mimic a human inspired approach to read measurements from a linear scale. As a test case we have picked reading level from a syringe and a measuring cylinder. For a randomly oriented syringe we carry out transformations to correct the orientation. To make the system efficient and robust, the area of interest is reduced to just the linear scale containing part of the image. After that, a series of features were extracted like the major makers, the corresponding digits, and the level indicator location, from which the final reading was calculated. Readings obtained using this system were also compared against human read values of the same instances and an accurate correspondence was observed.