DCT and DWT feature extraction and ANN classification based technique for non-destructive testing of materials

F.W. Zaki; M.M. Abd Elnaby; I.M. Elshafiey; A.S. Ashour; ASRT

doi:10.1109/NRSC.2001.929156

Back

Conference proceeding

DCT and DWT feature extraction and ANN classification based technique for non-destructive testing of materials

F.W. Zaki, M.M. Abd Elnaby, I.M. Elshafiey, A.S. Ashour and ASRT

Proceedings of the Eighteenth National Radio Science Conference. NRSC'2001 (IEEE Cat. No.01EX462), Vol.1, pp.35-44 vol.1

2001

DOI: https://doi.org/10.1109/NRSC.2001.929156

Abstract

Artificial neural networks

Computer simulation

Discrete cosine transforms

Discrete wavelet transforms

Eddy currents

Feature extraction

Impedance

Magnetic flux density

Nondestructive testing

Probes

Eddy current (EC) nondestructive testing (NDT) based on probe impedance and magnetic flux density in the defect regions is considered in this work. For this a numerical model is introduced for the development of the EC-NDT system using 3D finite element analysis. This model is used to simulate the material defects and prepares the data required for computer simulation of the EC-NDT system. The image data for three types of cracks in two types of materials are processed by discrete cosine (DCT) and discrete wavelet (DWT) transforms for feature extraction. Depending on the extracted features, the defects are classified using artificial neural network. A series of computer simulation experiments are carried out to assess the performance. 100% correct crack identification is achieved.

Metrics

1 Record Views

Details

Title: DCT and DWT feature extraction and ANN classification based technique for non-destructive testing of materials
Creators - without role: F.W. Zaki - Mansoura University
M.M. Abd Elnaby
I.M. Elshafiey
A.S. Ashour
ASRT
Publication Details: Proceedings of the Eighteenth National Radio Science Conference. NRSC'2001 (IEEE Cat. No.01EX462), Vol.1, pp.35-44 vol.1
Publisher: IEEE
Identifiers: 9951428608331
Academic Unit: King Saud University
Language: English
Resource Type: Conference proceeding