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

Table 1. Clustering results of K-means algorithm
View table
Table 1. Clustering results of K-means algorithm
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 2. Clustering results of K-medians algorithm
View table
Table 2. Clustering results of K-medians 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 3. Comparison of number of defect images before and after expansion
View table
Table 3. Comparison of number of defect images before and after expansion
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 4. Partial training parameters after modification
View table
Table 4. Partial training parameters after modification
Parameter Value
Epoch 150
Initial learning rate 0.0010
Learning rate when epoch is 50 0.0001
Momentum 0.9

Table 5. Comparison of ablation experimental results

View table

Table 5. Comparison of ablation experimental results

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 6. Performance of different algorithms

View table

Table 6. Performance of different algorithms

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

Tools

Get Citation

Copy Citation Text

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

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites