A Real-Time Automated Defect Detection System for Ceramic Pieces Manufacturing Process Based on Computer Vision with Deep Learning
Authors:
- Esteban CumbajinECEsteban Cumbajin
- Nuno RodriguesNuno Rodrigues
- Paulo CostaPaulo Costa
- Rolando MiragaiaRolando Miragaia
- Luís FrazãoLuís Frazão
- Nuno CostaNCNuno Costa
- Antonio Fernández-CaballeroAntonio Fernández-Caballero
- Jorge CarneiroJCJorge Carneiro
- Leire H. BuruberriLBLeire H. Buruberri
- António PereiraAPAntónio Pereira
Open Access
Abstract
Defect detection is a key element of quality control in today’s industries, and the process requires the incorporation of automated methods, including image sensors, to detect any potential defects that may occur during the manufacturing process. While there are various methods that can be used for inspecting surfaces, such as those of metal and building materials, there are only a limited number of techniques that are specifically designed to analyze specialized surfaces, such as ceramics, which can potentially reveal distinctive anomalies or characteristics that require a more precise and focused approach. This article describes a study and proposes an extended solution for defect detection on ceramic pieces within an industrial environment, utilizing a computer vision system with deep learning models. The solution includes an image acquisition process and a labeling platform to create training datasets, as well as an image preprocessing technique, to feed a machine learning algorithm based on convolutional neural networks (CNNs) capable of running in real time within a manufacturing environment. The developed solution was implemented and evaluated at a leading Portuguese company that specializes in the manufacturing of tableware and fine stoneware. The collaboration between the research team and the company resulted in the development of an automated and effective system for detecting defects in ceramic pieces, achieving an accuracy of 98.00% and an F1-Score of 97.29%.Keywords
Funding Information
- project STC 4.0 HP (POCI-01-0247-FEDER-069654, UIDB/04524/2020, 876659, PCI2020-112001)
- Fundação para a Ciência e a Tecnologia (POCI-01-0247-FEDER-069654, UIDB/04524/2020, 876659, PCI2020-112001)
- Portuguese national funds (POCI-01-0247-FEDER-069654, UIDB/04524/2020, 876659, PCI2020-112001)
- ECSEL Joint Undertaking (JU) (POCI-01-0247-FEDER-069654, UIDB/04524/2020, 876659, PCI2020-112001)
- Horizon 2020 Research Programme and participating countries (POCI-01-0247-FEDER-069654, UIDB/04524/2020, 876659, PCI2020-112001)
- MCIN/AEI/10.13039/501100011033 (POCI-01-0247-FEDER-069654, UIDB/04524/2020, 876659, PCI2020-112001)
This publication has 41 references indexed in Scilit:
- Vision-Based Crack Detection using Transfer Learning in Metal Forming Processes2019
- Training Accurate Binary Neural Networks from Scratch2019
- A survey on Image Data Augmentation for Deep LearningJournal of Big Data, 2019
- Surface Defects Detection Based on Adaptive Multiscale Image Collection and Convolutional Neural NetworksIEEE Transactions on Instrumentation and Measurement, 2019
- Dynamics-inspired feature extraction in semiconductor manufacturing processesJournal of Industrial Information Integration, 2019
- Damage Classification for Masonry Historic Structures Using Convolutional Neural Networks Based on Still ImagesComputer-Aided Civil and Infrastructure Engineering, 2018
- Defect Detection on Randomly Textured Surfaces by Convolutional Neural Networks2018
- Defect Detection in Porcelain Industry Based on Deep Learning Techniques2017
- Normalization in MALDI-TOF imaging datasets of proteins: practical considerationsAnalytical and Bioanalytical Chemistry, 2011
- Topological structural analysis of digitized binary images by border followingComputer Vision, Graphics, and Image Processing, 1985