Radial Basis Function Neural Network sebagai Pengklasifikasi Citra Cacat Pengelasan

Noorman Rinanto; Mohammad Thoriq Wahyudi; Agus Khumaidi

doi:10.21107/rekayasa.v11i2.4418

Radial Basis Function Neural Network sebagai Pengklasifikasi Citra Cacat Pengelasan

Noorman Rinanto, Mohammad Thoriq Wahyudi, Agus Khumaidi

Abstract

Tingginya resiko kesalahan manusia dalam inspeksi visual untuk cacat pengelasan yang masih mengandalkan kemampuan manusia sulit untuk dihindari. Oleh sebab itu, penelitian ini mengusulkan sebuah klasifikasi cacat las visual dengan menggunakan algoritma Radial Basis Function Neural Network (RBFNN). Masukan RBFNN berupa citra las yang terdiri dari 5 (lima) kelas cacat las visual dan 1 (satu) kelas citra las normal. Citra las tersebut diproses terlebih dahulu menggunakan metode ekstraksi fitur Fast Fourier Transform (FFT) dan Descreate Cosine Transform (DCT). Hasil kedua metode ekstraksi fitur tersebut kemudian akan saling dibandingkan untuk mengetahui kinerja RBFNN. Hasil pengujian menunjukkan bahwa sistem dengan metode FFT-RBFNN dapat menggolongkan citra cacat las dengan akurasi sebesar 91.67% dan DCT-RBFNN sekitar 83.33% dengan jumlah neuron hidden layer sebanyak 15 dan parameter spread adalah 4.

Kata Kunci: Radial Basis Function Neural Network (RBFNN), FFT, DCT, cacat las, klasifikasi.

Radial Basis Function Neural Network as a Weld Defect Classifiers

ABSTRACT

The high risk of human error in visual inspection of welding defects that still rely on human capabilities is difficult to avoid. Therefore, this study proposes a classification of visual welding defects using the Radial Base Function Neural Network (RBFNN) algorithm. The RBFNN input is in the form of a welding image consisting of 5 (five) visual welding defect classes and 1 (one) normal welding image class. The weld image is processed first using the Fast Fourier Transform (FFT) and Descreate Cosine Transform (DCT) feature extraction methods. The results of these two feature extraction methods will be compared to find out the RBFNN performance. The test results show that the system with FFT-RBFNN method can classify the image of weld defects with an accuracy of 91.67% and DCT-RBFNN around 83.33% with the number of hidden layer neurons as much as 15 and the parameters of spread are 4.

Keywords: Radial Basis Function Neural Network (RBFNN), FFT, DCT, weld defect, classification.

Keywords

Radial Basis Function Neural Network (RBFNN), FFT, DCT, weld defect, classification.

Full Text:

PDF

References

NDT Education Resource Center (2001). About NDT. https://www.nde-ed.org/AboutNDT/aboutndt.htm, Tanggal akses 4 Februari 2018.

X. Zhang, Z. Zhu, J. Xu, & S. Ren (2005). The Classification Algorithm of Defects in Weld Image based on Asymmetrical SVMs. Proceeding of International Conference on Control and Automation (ICCA2005), pp. 1215-1219.

F. Mekhalfa & N. Nacereddine (2014). Multiclass Classification of Weld Defects in Radiographic Images Based on Support Vector Machines. Proceeding of Tenth International Conference on Signal-Image Technology & Internet-Based Systems, pp. 1-6.

D. Gao, Y. Liu, X. Zhang, & Y. Liu (2006). Binary-tree Multi-Classifier for Welding Defects and Its Application Based on SVM. Proceeding of the 6th World Congress on Intelligent Control and Automation, Dalian, China, pp. 8509-8513.

J. Shao, H. Shi, D. Du, L. Wang, & H. Cao (2011). Automatic Weld Defect Detection in Real-time X-ray Images Based on Support Vector Machine. Proceeding of 4th International Congress on Image and Signal Processing, pp. 1842-1846.

Z. Sun, D. Ruan, Y. Ma, X. Hu, & X. Zhang (2009). Crack Defects Detection in Radiographic Weldment Images using FSVM and Beamlet Transform. Proceeding of Sixth International Conference on Fuzzy Systems and Knowledge Discovery, pp. 402-406.

T. W. Liao (2003). Classification of welding flaw types with fuzzy experts systems. Expert Systems with Applications, vol. 25(1), pp. 101-111.

R.Vilar, J. Zapata, and R. Ruiz (2009). An automatic system of classification of weld defects in radiographic images. NDT&E International, vol. 42(5), pp. 467-476.

N. Boaretto & T. M. Centeno (2016). Automated detection of welding defects in pipelines from radiographic images DWDI. NDT and E International, http://dx.doi.org/10.1016/j.ndteint.2016.11.003, Tanggal akses 12 Mei 2018.

N. Nacereddine, and M. Tridi (2005). Computer-aided shape analysis and classification of weld defects in industrial radiography based invariant attributes and neural networks. Proceeding of the 4 International Symposium on Image and Signal Processing and Analysis ISPA, pp. 88-93.

J. Mirapeix, P. B. Garcia-Allende, A. Cobo, O. M. Conde, and J. M. Lspez-Higuera (2007). Real time arc welding defect detection and classification with principal component analysis and artificial neural networks. NDT&E International, vol. 40(4), pp. 315-323.

I. Valavanis, and D. Kosmopoulos (2010), Multiclass defect detection and classification in weld radiographic images using geometric and texture features. Expert Systems with Applications, vol. 37, pp. 7606-7614.

K. Sudheera, N. M. Nandhitha, P. Nanekar, B. Venkatraman, & B. S. Rani (2013). Automated Weld Defect Classification Ultrasonic Signals using statistical moments on normal distribution curves of Wavelet co-efficient. Proceeding of International Conference on Advanced Electronic System (ICAES), pp. 24-28.

R. Ranjana, A. Reza Khan, C. Parikh, R. Jain, R. P. Mahto, S. Pal, S. K. Pal, & D. Chakravarty (2016). Classiﬁcation and identiﬁcation of surface defects in friction stir welding An image processing approach. Journal of Manufacturing Processes vol. 22, pp. 237–253.

A. Khumaidi, E. M. Yuniarno, M. H. Purnomo (2017). Welding Defect Classification Based on Convolution Neural Network (CNN) and Gaussian Kernel. Proceeding of International Seminar on Intelligent Technology and Its Application, pp. 261-265.

A. Kadir, and A. Susanto (2012). Pengolahan Citra, Penerbit ANDI Offset, Yogyakarta.

D. Chang, and W. Wu (1998). Image Contrast Enhancement Based on a Histogram Transformation of Local Standard Deviation. Journal IEEE Transactions on Medical Imaging, vol. 17(4), pp. 518-531.

M. A. Ghorbani, H. A. Zadeh, M. Isazadeh, & O. Terzi (2016). A Comparative study of artificial neural network (MLP, RBF) and support vector machine models for river flow prediction. Journal Enviromental Earth Sciences vol.75, pp. 476.

M. W. Mak, and G. G. Sexton (1993). Comparing Multi-Layer Perceptrons and Radial Basis Functions networks in speaker recognition. Journal of Microcomputer Applications, vol.16(2), pp. 147-159.

T. Kurban, and E. Beşdok (2009). A Comparison of RBF Neural Network Training Algorithms for Inertial Sensor Based Terrain Classification. Sensors 2009, vol. 9, pp. 6312-6329.