A new feature extraction process based on SFTA and DWT to enhance classification of ceramic tiles quality
- PDF / 2,282,398 Bytes
- 15 Pages / 595.276 x 790.866 pts Page_size
- 50 Downloads / 198 Views
ORIGINAL PAPER
A new feature extraction process based on SFTA and DWT to enhance classification of ceramic tiles quality Luan Casagrande1 · Luiz Antonio Buschetto Macarini1 Gustavo Medeiros de Araujo3
· Daniel Bitencourt1 · Antônio Augusto Fröhlich2 ·
Received: 4 November 2019 / Revised: 27 July 2020 / Accepted: 24 August 2020 / Published online: 24 September 2020 © Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract We propose a combination of image processing methods to detect ceramic tiles defects automatically. The primary goal is to identify faults in ceramic tiles, with or without texture. The process consists of four steps: preprocessing, feature extraction, optimization, and classification. In the second step, gray-level co-occurrence matrix, segmentation-based fractal texture analysis, discrete wavelet transform, local binary pattern, and a novel method composed of segmentation-based fractal texture analysis and discrete wavelet transform are applied. The genetic algorithm was used to optimize the parameters. In the classification step, k-nearest neighbor, support vector machine, multilayer perceptron, probabilistic neural network, and radial basis function network were assessed. Two datasets were used to validate the proposed process, totaling 782 ceramic tiles. In comparison with the other feature extraction methods commonly used, we demonstrate that the use of SFTA with DWT had a remarkable increase in the overall accuracy, without compromising computational time. The proposed method can be executed in real time on actual production lines and reaches a defect detection accuracy of 99.01% for smooth tiles and 97.89% for textured ones. Keywords Image processing · Pattern recognition · Manufacturing systems · Hyper-parameter tuning
1 Introduction The application of new image processing and machine learning techniques to the inspection of the quality control in production lines has been driving the improvement
B
Luiz Antonio Buschetto Macarini [email protected] Luan Casagrande [email protected] Daniel Bitencourt [email protected] Antônio Augusto Fröhlich [email protected] Gustavo Medeiros de Araujo [email protected]
1
Department of Computing, Federal University of Santa Catarina, Araranguá, Brazil
2
Computer Science Department, Federal University of Santa Catarina, Florianópolis, Brazil
3
Information Science Department, Federal University of Santa Catarina, Florianópolis, Brazil
of manufacturing systems [1]. Machine learning and image processing are being applied to optimize the production and quality control processes [2] in industries such as textile, glass, food, and even ceramics. The combination of real-time image processing techniques, statistical data, and machine learning is often used to identify flaws and improve production [3]. Nowadays, the ceramic industry has many processes already fully automated. The only step that usually still requires intense human intervention is quality control [4]. However, human-based quality contro
Data Loading...
