Treffer: Utilizing Machine Vision and Deep Learning for Quality Control in Pharmaceutical Lab Tools Manufactured Via Injection Molding.

This research presents a machine vision inspection system for quality control of injection molded parts used in pharmaceutical lab tools. Industries demand fast and accurate inspection systems, and machine vision offers automation, consistency, precision, and high-speed capabilities, making it an ideal solution. The system integrates National Instruments Vision Builder for Automated Inspection (VBAI) and MATLAB to perform defect detection, dimensional verification, and feature validation. Eppendorf's TipOne® Filter Tip Refills, known for precision and contamination prevention, were inspected to demonstrate the system's utility. The hardware setup features top and front view cameras, LED boards for uniform lighting, and opaque covers to minimize external interference, ensuring consistent image quality. Six inspection programs utilize traditional algorithms and deep learning models to measure dimensions, detect missing features, and identify surface irregularities, achieving 95% accuracy across all tasks. These results highlight the system's potential to replace manual inspections, enabling real time, high throughput quality control. Future enhancements include integrating high resolution cameras and advanced machine learning to improve defect classification. This research emphasizes the transformative potential of machine vision in advancing manufacturing quality assurance and automation across industries like pharmaceuticals, automotive, and consumer goods. [ABSTRACT FROM AUTHOR]

Copyright of EPJ Web of Conferences is the property of EDP Sciences and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)