Automated Surface Inspection Using Gabor Filters

Abstract

In this paper we present a machine vision system for automatic inspection of defects in textured surfaces found in industry. The defects to be inspected are those that appear as local anomalies embedded in a homogeneous texture. The proposed method is based on a Gabor filtering scheme that computes the output response of energy from the convolution of a textured image with a specific Gabor filter. The best parameters of a Gabor filter is selected so that the energy of the homogeneous texture is zero, and any unpredictable defects will generate significantly large energy values. A simple thresholding scheme then follows to discriminate between homogeneous regions and defective regions in the filtered image. This transforms texture differences into detectable filter output. The experiments on structural textures such as textile fabrics and milled surfaces, and statistical textures such as leather and sandpaper have shown the effectiveness of the proposed method.

Super-fit control adaptation in memetic differential evolution frameworks

“…Gabor filters are often used in vision system applications (Weldon and Higgins 1996;Sun et al 2005;Tsa and Wu 2000). A common use is to apply Gabor filters as a filter bank (see Manjunath and Haley 2000) to dissect image signals into oriented band sections in frequency space and use the obtained signals as features for learning systems.…”

A vision inspection system for the surface defects of strongly reflected metal based on multi-class SVM

“…Co-occurrence matrices method is one of statistic methods in the spatial domain. Techniques in the spectral domain extract textural features by conducting frequency transforms such as Fourier transform (Tsai & Huang, 2003), Gabor transform (Tsa & Wu, 2000), or wavelet transform (Lee, Choi, Choi, Kim, & Choi, 1996;Lee, Choi, Choi, & Choi, 1997). Fourier transform is a global method, which just depicts the spatial-frequency distribution without regarding to the spatial domain information.…”

Defect detection in periodic patterns using a multi-band-pass filter

“…Most existing approaches for defect inspection in periodic patterns can be divided into three main classes: (1) template matching [1][2][3][4][5][6][7][8][9][10][11][12][13]; (2) neural networks [14][15][16][17][18][19][20]; and (3) filter approaches [21][22][23][24][25][26][27][28][29][30][31][32][33]. A few other studies have reported approaches other than the abovementioned [34].…”

“…The third class of detection is the use of filter-based techniques [21][22][23][24][25][26][27][28][29][30][31][32][33] such as the Gabor filter [21][22][23][24], the wavelet transform [25][26][27], and the discrete Fourier transform (DFT) [28][29][30][31][32][33]. The Gabor filter uses a Gaussian-type bandpass filter to extract defects; here, the defect spectrum must be exactly mapped in order to extract the defects [21][22][23][24].…”

“…The Gabor filter uses a Gaussian-type bandpass filter to extract defects; here, the defect spectrum must be exactly mapped in order to extract the defects [21][22][23][24]. The wavelet transform approach uses different order bandpass filters and down-sampling techniques to separate the background of periodic patterns.…”