Visual inspection of soldering defects on board surfaces against complex backgrounds

Number	Dilation	Layer	s	Output size
0	-	Focus	-	320×320×32
1	-	SPD-Conv	-	160×160×64
2	1	DeCSPlayer	-	160×160×64
3	-	SPD-Conv	2	80×80×128
4	2	DeCSPlayer	-	80×80×128
5	-	SPD-Conv	2	40×40×256
6	3	DeCSPlayer	-	40×40×256
7	-	SPD-Conv	2	20×20×512
8	-	SPP	-	20×20×512
9	5	DeCSPlayer	-	20×20×512

Table 2. Camera parameters during data collection
View table
View in Article
Table 2. Camera parameters during data collection
项目参数
相机型号 MV-CS060-10UC-PRO
光圈 F4
焦距 8 mm
光源类型 Ring light
曝光时间 50 000 μs
分辨率 3 072×2 048
物距 100 mm
视野 50 mm×35 mm

Table 3. Number of defects in various categories in the dataset
View table
View in Article
Table 3. Number of defects in various categories in the dataset
缺陷类别缺陷数目
Aiguille 2 487
Dissymmetry 1 667
Holes 1 923
Interconnect pad 4 069

Table 4. Results of the ablation study

View table

View in Article

Table 4. Results of the ablation study

方法	图像尺寸	mAP_0.5/%	mAP_0.5：0.95/%	Params/Mb	FPS
YOLOX-S	640	92.5	60.8	8.94	106
YOLOX-S+SFEM	640	93.6	64.7	9.73	89
YOLOX-S+DeConv	640	94.5	64.6	9.36	90
YOLOX-S+SPD-Conv	640	94.3	64.9	13.64	100
YOLOX-S+SPD-Conv+SFEM	640	94.8	64.7	14.43	90
YOLOX-S+SPD-Conv+SFEM+DeConv	640	95.3	65.0	14.85	86

Table 5. Impact of different r values in DeConv on the optimal model accuracy
View table
View in Article
Table 5. Impact of different r values in DeConv on the optimal model accuracy
方法 mAP_0.5/% mAP_0.5：0.95/% Params /Mb FPS
r=2 94.6 64.7 15.92 85
r=3 95.3 65.0 14.85 86
r=4 95.1 64.9 14.54 87
r=5 94.7 65.1 14.41 87

Table 6. Impact of different dilation values in the backbone of PCBNet on the optimal model accuracy

View table

View in Article

Table 6. Impact of different dilation values in the backbone of PCBNet on the optimal model accuracy

空洞率	mAP_0.5 /%	mAP_0.5：0.95 /%	Params /Mb	FPS
2，2，2，2	95.0	65.4	14.85	87
1，2，1，2	95.2	65.3	14.85	88
1，6，12，18	95.3	65.0	14.85	86
1，2，5，7	94.9	65.0	14.85	86
1，2，3，5	95.4	65.5	14.85	83
1，2，5，1	94.9	65.0	14.85	87
1，2，9，12	95.1	65.2	14.85	86

Table 7. Performance statistics of the model with different numbers of training samples
View table
View in Article
Table 7. Performance statistics of the model with different numbers of training samples
样本数
mAP_0.5
/%
mAP_0.5：0.95
/%
Params
/Mb
FPS
80% 95.4 65.5 14.85 87
70% 95.2 65.3 14.85 87
60% 95.0 65.2 14.85 87

Table 8. Results compared to other methods（For statistical convenience， aiguille is simplified as A， disymmetry is simplified as D， holes is simplified as H， and Interconnect pad is simplified as I-P）

View table

View in Article

Table 8. Results compared to other methods（For statistical convenience， aiguille is simplified as A， disymmetry is simplified as D， holes is simplified as H， and Interconnect pad is simplified as I-P）

模型	主干	AP_0.5（%）				mAP_0.5 /%	mAP_0.75 /%	mAP_0.5∶0.95 /%	FPS	Params /Mb
模型	主干	A	D	H	I-P	mAP_0.5 /%	mAP_0.75 /%	mAP_0.5∶0.95 /%	FPS	Params /Mb
Faster-RCNN	resnet50	61.8	63.8	66.7	85.3	69.4	15.3	28.5	30	136.75
CenterNet	resnet50	88.7	91.7	95.3	92.7	92.1	61.0	55.2	101	32.67
RetinaNet	resnet50	83.8	87.9	91.8	92.9	89.1	61.0	54.9	53	36.39
EfficientDetv1	EfficientNet-B0	50.8	68.8	71.0	86.2	69.2	25.4	32.7	33	3.83
YOLOV4-Tiny		63.7	84.8	89.6	89.1	81.8	28.3	37.9	192	5.88
YOLOV5-s	C3	80.8	80.9	92.0	91.6	86.3	56.0	51.0	92	7.07
YOLOV8-s	C2f	90.9	93.9	94.9	94.4	93.5	76.8	63.4	114	11.14
CFPNet	-	87.7	90.6	96.1	96.5	92.7	71.9	60.8	89	13.14
YOLOX-s	-	86.7	92.1	95.6	95.5	92.5	72.3	60.8	106	8.94
YOLOX-m	-	90.8	92.1	97.3	96.4	93.8	75.5	63.0	74	25.28
YOLO-PCB	-	54.0	80.0	89.5	64.2	71.9	65.8	52.6	95	8.9
MDVI	-	75.8	87.7	94.0	93.9	87.8	43.3	46.0	161	12.22
RTDD-LCD	-	68.8	86.8	93.9	92.8	85.6	34.9	41.6	73	25.08
PCBNet	-	91.2	94.8	97.4	98.2	95.4	79.0	65.5	83	14.85

Table 9. Dataset splitting
View table
View in Article
Table 9. Dataset splitting
任务图像尺寸数目
训练 600×600×3 8 460
验证 600×600×3 961
测试 600×600×3 1 067

Table 10. Results compared to other methods

View table

View in Article

Table 10. Results compared to other methods

模型	模型版本	主干	mAP_0.5/%	mAP_0.75/%	mAP_0.5∶0.95/%	FPS	Params/Mb
Faster-RCNN	-	resnet50	72.6	11.2	28.4	30	136.75
CenterNet	-	resnet50	97.7	46.3	52.1	101	32.67
RetinaNet	-	resnet50	92.7	43.4	49.3	53	36.39
EfficientDetv1	-	EfficientNet-B0	85.6	38.6	43.4	33	3.83
YOLOV4-Tiny	-		97.2	32.6	46.6	192	5.88
YOLOV5	s	C3	98.3	60.0	56.6	92	7.07
YOLOV8	s	C2f	99.2	78.4	65.2	114	11.14
CFPNet	s	-	98.8	65.3	59.3	89	13.14
YOLOx	s	-	98.2	59.6	57.0	106	8.94
YOLOX	m	-	99.1	86.7	76.5	74	25.28
YOLO-PCB	-	-	96.7	71.5	61.3	95	8.9
MDVI	-	-	98.2	41.4	50.5	161	12.22
RTDD-LCD	-	-	97.6	39.0	49.1	73	25.08
PCBNet	-	-	99.5	88.7	73.2	83	14.85

Tools

Get Citation

Copy Citation Text

Liying ZHU, Sen WANG, Aiping SHEN, Xuangang LI. Visual inspection of soldering defects on board surfaces against complex backgrounds[J]. Optics and Precision Engineering, 2024, 32(14): 2256

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites

Paper Information

Category:

Received: Mar. 13, 2024

Accepted: --

Published Online: Sep. 27, 2024

The Author Email: WANG Sen (wangsen0401@126.com)

DOI:10.37188/OPE.20243214.2256

Topics

laser devices and laser physics

Lasers and Laser Optics

Laser physics

laser manufacturing

Instrumentation, Measurement and Metrology

Table 1. Dilatation rate configuration table in the backbone

Table 1. Dilatation rate configuration table in the backbone

Table 2. Camera parameters during data collection

Table 2. Camera parameters during data collection

Table 3. Number of defects in various categories in the dataset

Table 3. Number of defects in various categories in the dataset

Table 4. Results of the ablation study

Table 4. Results of the ablation study

Table 5. Impact of different r values in DeConv on the optimal model accuracy

Table 5. Impact of different r values in DeConv on the optimal model accuracy

Table 6. Impact of different dilation values in the backbone of PCBNet on the optimal model accuracy

Table 6. Impact of different dilation values in the backbone of PCBNet on the optimal model accuracy

Table 7. Performance statistics of the model with different numbers of training samples

Table 7. Performance statistics of the model with different numbers of training samples

Table 8. Results compared to other methods（For statistical convenience， aiguille is simplified as A， disymmetry is simplified as D， holes is simplified as H， and Interconnect pad is simplified as I-P）

Table 8. Results compared to other methods（For statistical convenience， aiguille is simplified as A， disymmetry is simplified as D， holes is simplified as H， and Interconnect pad is simplified as I-P）

Table 9. Dataset splitting

Table 9. Dataset splitting

Table 10. Results compared to other methods

Table 10. Results compared to other methods

微信扫一扫：分享