Review of vision-based steel surface inspection systems

Neogi, Nirbhar; Mohanta, Dusmanta K; Dutta, Pranab K

doi:10.1186/1687-5281-2014-50

EURASIP Journal on Image and Video Processing

Table 4 Comparison of defect classification systems

From: Review of vision-based steel surface inspection systems

Paper	Method		Type of defects	Sample size	Features	Classification accuracy (%)	Resolution (Across x along) (mm)	Speed of steel object	Real-time operation
Paper	Detection	Classification	Type of defects	Sample size	Features	Classification accuracy (%)	Resolution (Across x along) (mm)	Speed of steel object	Real-time operation
[46] - slab	Robert edge filter, zonal thresholding, edge connectivity	Statistical tree classifier	Crack, pits, tear, scab, rollmark, under fill, bleeder		17 geometric		0.076 × 1.27	4 in./s (36.6 m/min)	Suitable
[70] - hot strip	Five wavelets (feature extraction)	VVRKFA, SVM	24 types (details in paper)	1,432 images	3 to 9 elements - 5 wavelets	93.8	1 × 1	20 m/s
[36] - hot strip	Co-occurrence matrix	NN-BP, GMDH, SOM	RIS, bruise, rolled in bruise, scratch, lamination	1,084 cases	24 spatial, textural	NN-BP 83.5 (ave.)
[62] - hot strip	FFT (feature extraction), GA	LVQ	Crack, pits, scar, rollmark, shell, cross	485 images	54 frequency domain	84 to 93
[62] - hot strip	FFT (feature extraction), GA	LVQ	texture, pseudo	485 images	54 frequency domain	84 to 93
[32] - hot strip		NN-BP	Shell, hole, pit/scab, residue scale, coil break, slip mark, rust	255 samples	4 geometric	98.75		10 to 15 m/s
[31] - cold strip	FFT (filtering), local entropy, thresholding, morphology	NN-BP, fuzzy logic	Sticking, emulsion rust, under pickled, dirty surface, anneal stain	2,300 images	9 statistical	NN-BP: 97, Fuzzy logic: 82	0.37		Suitable
[76] - cold strip	Sobel edge detector, region growing	Fuzzy logic	Scaling, shrunken leaf, cusping, file mark, cleavage crack, tear	15 to 20 defects/class	Geometric, fractal	85 to 95		6 m/s	Suitable
[26] - cold strip	Thresholding (six types)	Decision tree discrimination logic	Scab, sliver, scale, gauge, scratch, roll mark, oil spot	196 defects		95.5	0.17 × 1.25	1,400 m/min (23 m/s)	Suitable
[89] - cold strip		LVQ	Rust, lamination, rollmark, scratch, weld, and stain	135 images	17 feature +11 reference	Approximately 68 to 96		5 m/s
[63] - cold strip	Multifractal	NN-BP	Sticking, emulsion rust, under pickled, dirty surface, anneal stain defect	2,300 images	10 geometric, gray level	97.9	0.37
[43] - cold strip	Morphological, thresholding	Hough transform: line defect	Welding, clamp, hole, oxidation, waveform, exfoliation	300 images	6 components	Line defect: 98.
[43] - cold strip	Morphological, thresholding	PCA-SOM: complex shape	Welding, clamp, hole, oxidation, waveform, exfoliation	300 images	6 components	Complex shape: 77
[87] - cold strip	Sobel edge detector, threshold, special filter	Fuzzy logic	Large population of inclusions	212 images	4	95
[83] - cold strip	Difference image	SVM	Line scab, pickle patch, hole, slip mark, oil drop, pit	1,200 images	54 geometric, gray level	92.4
[82] - cold strip		Weak classifier	Serrated edge, scratch, shell, inclusion, weld, wrinkles.	500 images	Extended Haar rectangle features	94
[77] - cold strip		Modified NN BP	Flash, roller moulage, oxidation skin, hole, crack	300		94.34
[59] - rod/bar	Special horizontal, vertical, diagonal edge filters	Hierarchical	Seam, scratch, roll mark, overfill	663 images	12 geometric, gray level	NN BP: 90.66, RVM: 91.21		15 m/s	Suitable
[59] - rod/bar	Special horizontal, vertical, diagonal edge filters	NN BP, RVM	Seam, scratch, roll mark, overfill	663 images	12 geometric, gray level	NN BP: 90.66, RVM: 91.21		15 m/s	Suitable
[85] - rod/bar		Process knowledge-based multiclass SVM (PK-MSVM)	Seams, longitudinal cracks, scales, transverse mid-surface cracks and transverse corner cracks	600 bars (20,140 defects)	4 process features + image data set	81.4 to 93.9

Back to article page