Surface Defect Detection Algorithm of Aluminum Profile Based on AM-YOLOv3 Model

Lianshan Sun; Jingxue Wei; Dengming Zhu; Min Shi

doi:10.3788/LOP202158.2415007

Journals >Laser & Optoelectronics Progress >Volume 58 >Issue 24 >Page 2415007 > Article

Laser & Optoelectronics Progress
Vol. 58, Issue 24, 2415007 (2021)

Surface Defect Detection Algorithm of Aluminum Profile Based on AM-YOLOv3 Model

Lianshan Sun¹, Jingxue Wei^1、*, Dengming Zhu², and Min Shi³

Author Affiliations

¹School of Electronic Information and Artificial Intelligence, Shaanxi University of Science and Technology, Xi'an, Shaanxi 710021, China

²Foresight Research Laboratory, Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100080, China

³School of Control and Computer Engineering, North China Electric Power University, Beijing 102206, China

show less

DOI: 10.3788/LOP202158.2415007 Cite this Article Set citation alerts

Lianshan Sun, Jingxue Wei, Dengming Zhu, Min Shi. Surface Defect Detection Algorithm of Aluminum Profile Based on AM-YOLOv3 Model[J]. Laser & Optoelectronics Progress, 2021, 58(24): 2415007 Copy Citation Text

show less

Fig. 1. Overall network structure of YOLOv3

Download full size

Fig. 2. Overall network structure of AM-YOLOv3

Download full size

Fig. 3. Structural diagram of attention guidance module

Download full size

Fig. 4. Schematic diagram of twin-towers structure

Download full size

Fig. 5. Five types of defects in aluminum profile dataset. (a) Non-conduction; (b) scratch; (c) wrinkle; (d) jet; (e) spot

Download full size

Fig. 6. Data enhancement results. (a) Original image; (b) enhanced images

Download full size

Fig. 7. M_AP of five types of defects

Download full size

Fig. 8. mAP curve

Download full size

Fig. 9. Defects detection effect. (a1)(a2) Non-conduction; (b1)(b2) scratch; (c1)(c2) wrinkle; (d1)(d2) jet; (e1)(e2) spot

Download full size

Size	Clustering parameter
13×13	(392, 33)	(408, 91)	(414, 182)
26×26	(224, 163)	(353, 17)	(365, 57)
52×52	(87, 90)	(94, 30)	(184, 44)
104×104	(9, 12)	(21, 25)	(30, 60)
Precision	71.14%

Table 1. Clustering results of K-means algorithm

Size	Clustering parameter
13×13	(416, 75)	(416, 102)	(416, 190)
26×26	(179, 44)	(416, 17)	(416, 39)
52×52	(58, 27)	(94, 30)	(113, 28)
104×104	(8, 11)	(85, 70)	(25, 46)
Precision	74.41%

Table 2. Clustering results of K-medians algorithm

Class	Original image	Enhanced image
Non-conduction	375	2250
Scratch	104	2080
Wrinkle	151	2114
Jet	66	2046
Spot	104	2080
Total	800	10570

Table 3. Comparison of number of defect images before and after expansion

Parameter	Value
Epoch	150
Initial learning rate	0.0010
Learning rate when epoch is 50	0.0001
Momentum	0.9

Table 4. Partial training parameters after modification

Algorithm	K-medians	Four feature scales	FAG	Twin-towers structure	M_mAP /%	f_FPS /(frame·s^-1)
YOLOv3	×	×	×	×	92.74	48.83
Group A	√	×	×	×	93.66	56.33
Group B	√	√	×	×	96.31	50.28
Group C	√	√	√	×	98.17	47.85
AM-YOLOv3	√	√	√	√	99.05	43.94

Table 5. Comparison of ablation experimental results

Algorithm	Backbone	AP of non-conductiondetection /%	AP of scratchdetection /%	AP of jet detection /%	AP of wrinkle detection /%	AP of spot detection /%	M_mAP /%	f_FPS /(frame·s^-1)
Faster R-CNN^[8]	VGG16	87.41	74.56	79.97	96.65	22.25	72.17	17.21
SSD^[9]	VGG16	89.79	79.88	88.96	98.92	40.62	79.63	77.17
YOLOv3^[11]	DarkNet-53	93.92	95.18	98.50	99.80	76.32	92.74	48.83
YOLOv3	ResNet152	94.85	93.97	98.62	99.26	75.80	92.50	27.37
YOLOv4^[12]	CSPDarknet53	95.21	95.79	98.99	99.76	89.96	95.94	45.29
YOLOv5^[13]	CSPDarknet53	96.83	97.34	99.95	99.98	93.58	97.53	42.37
CenterNet^[15]	Resnet-101	85.87	68.33	79.89	99.15	43.93	75.43	70.61
shuzhilian ai^[26]	Resnet-101	94.48	81.80	67.73	98.30	51.12	78.69	21.43
AM-YOLOv3	DarkNet-53	98.13	98.00	100.00	99.96	99.12	99.05	43.94

Table 6. Performance of different algorithms

Lianshan Sun, Jingxue Wei, Dengming Zhu, Min Shi. Surface Defect Detection Algorithm of Aluminum Profile Based on AM-YOLOv3 Model[J]. Laser & Optoelectronics Progress, 2021, 58(24): 2415007

Download Citation

Set citation alerts for the article

Tools

Set citation alerts for the article

Save the article for my favorites

Paper Information