A Machine Learning Method for Detection of Surface Defects on Ceramic Tiles Using Convolutional Neural Networks
We propose a simple but effective convolutional neural network to learn the similarities between closely related raw pixel images for feature representation extraction and classification through the initialization of convolutional kernels from learned filter kernels of the network. The binary-class...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/11/1/55 |
| _version_ | 1797499289684934656 |
|---|---|
| author | Okeke Stephen Uchenna Joseph Maduh Mangal Sain |
| author_facet | Okeke Stephen Uchenna Joseph Maduh Mangal Sain |
| author_sort | Okeke Stephen |
| collection | DOAJ |
| description | We propose a simple but effective convolutional neural network to learn the similarities between closely related raw pixel images for feature representation extraction and classification through the initialization of convolutional kernels from learned filter kernels of the network. The binary-class classification of sigmoid and discriminative feature vectors are simultaneously learned together contrasting the handcrafted traditional method of feature extractions, which split feature-extraction and classification tasks into two different processes during training. Relying on the high-quality feature representation learned by the network, the classification tasks can be efficiently conducted. We evaluated the classification performance of our proposed method using a collection of tile surface images consisting of cracked surfaces and no-cracked surfaces. We tried to classify the tiny-cracked surfaces from non-crack normal tile demarcations, which could be useful for automated visual inspections that are labor intensive, risky in high altitudes, and time consuming with manual inspection methods. We performed a series of comparisons on the results obtained by varying the optimization, activation functions, and deployment of different data augmentation methods in our network architecture. By doing this, the effectiveness of the presented model for smooth surface defect classification was explored and determined. Through extensive experimentation, we obtained a promising validation accuracy and minimal loss. |
| first_indexed | 2024-03-10T03:45:20Z |
| format | Article |
| id | doaj.art-5a9295ed4738420ea70343823268a29b |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-10T03:45:20Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-5a9295ed4738420ea70343823268a29b2023-11-23T11:22:12ZengMDPI AGElectronics2079-92922021-12-011115510.3390/electronics11010055A Machine Learning Method for Detection of Surface Defects on Ceramic Tiles Using Convolutional Neural NetworksOkeke Stephen0Uchenna Joseph Maduh1Mangal Sain2Department of Ubiquitous Information Technology, Dongseo University, Busan 47011, KoreaDepartment of Civil Engineering, Faculty of Engineering, Yeungnam University, Gyeongsan 38541, KoreaDivision of Information and Computer Engineering, Dongseo University, Busan 47011, KoreaWe propose a simple but effective convolutional neural network to learn the similarities between closely related raw pixel images for feature representation extraction and classification through the initialization of convolutional kernels from learned filter kernels of the network. The binary-class classification of sigmoid and discriminative feature vectors are simultaneously learned together contrasting the handcrafted traditional method of feature extractions, which split feature-extraction and classification tasks into two different processes during training. Relying on the high-quality feature representation learned by the network, the classification tasks can be efficiently conducted. We evaluated the classification performance of our proposed method using a collection of tile surface images consisting of cracked surfaces and no-cracked surfaces. We tried to classify the tiny-cracked surfaces from non-crack normal tile demarcations, which could be useful for automated visual inspections that are labor intensive, risky in high altitudes, and time consuming with manual inspection methods. We performed a series of comparisons on the results obtained by varying the optimization, activation functions, and deployment of different data augmentation methods in our network architecture. By doing this, the effectiveness of the presented model for smooth surface defect classification was explored and determined. Through extensive experimentation, we obtained a promising validation accuracy and minimal loss.https://www.mdpi.com/2079-9292/11/1/55visual inspectionsurface defect classificationconvolutional neural networkdata augmentationdefect class classification |
| spellingShingle | Okeke Stephen Uchenna Joseph Maduh Mangal Sain A Machine Learning Method for Detection of Surface Defects on Ceramic Tiles Using Convolutional Neural Networks Electronics visual inspection surface defect classification convolutional neural network data augmentation defect class classification |
| title | A Machine Learning Method for Detection of Surface Defects on Ceramic Tiles Using Convolutional Neural Networks |
| title_full | A Machine Learning Method for Detection of Surface Defects on Ceramic Tiles Using Convolutional Neural Networks |
| title_fullStr | A Machine Learning Method for Detection of Surface Defects on Ceramic Tiles Using Convolutional Neural Networks |
| title_full_unstemmed | A Machine Learning Method for Detection of Surface Defects on Ceramic Tiles Using Convolutional Neural Networks |
| title_short | A Machine Learning Method for Detection of Surface Defects on Ceramic Tiles Using Convolutional Neural Networks |
| title_sort | machine learning method for detection of surface defects on ceramic tiles using convolutional neural networks |
| topic | visual inspection surface defect classification convolutional neural network data augmentation defect class classification |
| url | https://www.mdpi.com/2079-9292/11/1/55 |
| work_keys_str_mv | AT okekestephen amachinelearningmethodfordetectionofsurfacedefectsonceramictilesusingconvolutionalneuralnetworks AT uchennajosephmaduh amachinelearningmethodfordetectionofsurfacedefectsonceramictilesusingconvolutionalneuralnetworks AT mangalsain amachinelearningmethodfordetectionofsurfacedefectsonceramictilesusingconvolutionalneuralnetworks AT okekestephen machinelearningmethodfordetectionofsurfacedefectsonceramictilesusingconvolutionalneuralnetworks AT uchennajosephmaduh machinelearningmethodfordetectionofsurfacedefectsonceramictilesusingconvolutionalneuralnetworks AT mangalsain machinelearningmethodfordetectionofsurfacedefectsonceramictilesusingconvolutionalneuralnetworks |