Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Computer Vision-Based Quality Assessment Technique for the automatic control of consumables for analytical laboratories

Meriam Zribi, Paolo Pagliuca, Francesca Pitolli

TL;DR

The paper addresses automatic quality control in plastic lab consumables by detecting the presence of a transparent anticoagulant in test tubes using a custom CNN, ConvNet3_4, and a transfer-learning comparison with several pre-trained networks. It studies two output configurations, $2_{{output-labels}}$ and $4_{{output-labels}}$, and evaluates performance through 5-fold cross-validation, data augmentation, and a dedicated lab-generated dataset of $9246$ images. ConvNet3_4 achieves near-perfect accuracy on the simpler task and high accuracy on the more complex one, while demonstrating superior generalization relative to pre-trained models. The results support industrial deployment for real-time monitoring, with future work focused on reducing training oscillations and expanding the dataset to further validate generalization.

Abstract

The rapid growth of the Industry 4.0 paradigm is increasing the pressure to develop effective automated monitoring systems. Artificial Intelligence (AI) is a convenient tool to improve the efficiency of industrial processes while reducing errors and waste. In fact, it allows the use of real-time data to increase the effectiveness of monitoring systems, minimize errors, make the production process more sustainable, and save costs. In this paper, a novel automatic monitoring system is proposed in the context of production process of plastic consumables used in analysis laboratories, with the aim to increase the effectiveness of the control process currently performed by a human operator. In particular, we considered the problem of classifying the presence or absence of a transparent anticoagulant substance inside test tubes. Specifically, a hand-designed deep network model is used and compared with some state-of-the-art models for its ability to categorize different images of vials that can be either filled with the anticoagulant or empty. Collected results indicate that the proposed approach is competitive with state-of-the-art models in terms of accuracy. Furthermore, we increased the complexity of the task by training the models on the ability to discriminate not only the presence or absence of the anticoagulant inside the vial, but also the size of the test tube. The analysis performed in the latter scenario confirms the competitiveness of our approach. Moreover, our model is remarkably superior in terms of its generalization ability and requires significantly fewer resources. These results suggest the possibility of successfully implementing such a model in the production process of a plastic consumables company.

A Computer Vision-Based Quality Assessment Technique for the automatic control of consumables for analytical laboratories

TL;DR

The paper addresses automatic quality control in plastic lab consumables by detecting the presence of a transparent anticoagulant in test tubes using a custom CNN, ConvNet3_4, and a transfer-learning comparison with several pre-trained networks. It studies two output configurations, and , and evaluates performance through 5-fold cross-validation, data augmentation, and a dedicated lab-generated dataset of images. ConvNet3_4 achieves near-perfect accuracy on the simpler task and high accuracy on the more complex one, while demonstrating superior generalization relative to pre-trained models. The results support industrial deployment for real-time monitoring, with future work focused on reducing training oscillations and expanding the dataset to further validate generalization.

Abstract

The rapid growth of the Industry 4.0 paradigm is increasing the pressure to develop effective automated monitoring systems. Artificial Intelligence (AI) is a convenient tool to improve the efficiency of industrial processes while reducing errors and waste. In fact, it allows the use of real-time data to increase the effectiveness of monitoring systems, minimize errors, make the production process more sustainable, and save costs. In this paper, a novel automatic monitoring system is proposed in the context of production process of plastic consumables used in analysis laboratories, with the aim to increase the effectiveness of the control process currently performed by a human operator. In particular, we considered the problem of classifying the presence or absence of a transparent anticoagulant substance inside test tubes. Specifically, a hand-designed deep network model is used and compared with some state-of-the-art models for its ability to categorize different images of vials that can be either filled with the anticoagulant or empty. Collected results indicate that the proposed approach is competitive with state-of-the-art models in terms of accuracy. Furthermore, we increased the complexity of the task by training the models on the ability to discriminate not only the presence or absence of the anticoagulant inside the vial, but also the size of the test tube. The analysis performed in the latter scenario confirms the competitiveness of our approach. Moreover, our model is remarkably superior in terms of its generalization ability and requires significantly fewer resources. These results suggest the possibility of successfully implementing such a model in the production process of a plastic consumables company.
Paper Structure (21 sections, 9 equations, 13 figures, 14 tables)

This paper contains 21 sections, 9 equations, 13 figures, 14 tables.

Table of Contents

  1. Introduction
  2. The Monitoring System
  3. Materials and Methods
  4. The CNN model
  5. Feature Extraction Block (FEB)
  6. Classification Block (CB)
  7. Backpropagation algorithm
  8. Results
  9. Training phase
  10. Transfer learning
  11. Dataset
  12. Cross-validation
  13. $2_{{output-labels}}$ case
  14. ConvNet3_4 model
  15. Pre-trained models
  16. ...and 6 more sections

Figures (13)

  • Figure 1: The monitoring system. Tubes (blue items) run within the tunnel. The system is illuminated by led cards (green items). A photosensor (orange item) gives the signal for the acquisition of the image.
  • Figure 2: Example of analyzed test tubes. Vials have a label on the side wall. The unit of measurement is the milliliter. (left) a small vial (height: 10 cm, diameter: 1 cm, capacity: 6 ml); (right) a large vial (height: 10 cm, diameter: 1.3 cm, capacity: 9 ml).
  • Figure 3: Images recorded by the camera. Left figure: a tube containing anticoagulant. Right figure: an empty tube. Figure taken from zribi2023convolutional.
  • Figure 4: Deep Neural Network Architecture.
  • Figure 5: Illustration of the ConvNet3_4 model.
  • ...and 8 more figures