Surface defect detection of solar cells using local and global feature fusion

Zhiyong Tao; Yan He; Sen Lin; Tingjun Yi; Yaosheng Zhang

doi:10.12086/oee.2024.230292

Journals >Opto-Electronic Engineering >Volume 51 >Issue 1 >Page 230292-1 > Article

Opto-Electronic Engineering
Vol. 51, Issue 1, 230292-1 (2024)

Surface defect detection of solar cells using local and global feature fusion

Zhiyong Tao¹, Yan He^1、*, Sen Lin², Tingjun Yi¹, and Yaosheng Zhang¹

Author Affiliations

¹School of Electronic and Information Engineering, Liaoning Technical University, Huludao, Liaoning 125105, China

²School of Automation and Electrical Engineering, Shenyang Ligong University, Shenyang, Liaoning 110159, China

show less

DOI: 10.12086/oee.2024.230292 Cite this Article

Zhiyong Tao, Yan He, Sen Lin, Tingjun Yi, Yaosheng Zhang. Surface defect detection of solar cells using local and global feature fusion[J]. Opto-Electronic Engineering, 2024, 51(1): 230292-1 Copy Citation Text

show less

Fig. 1. Coordinate attention

Download full size | View in the Article

Fig. 2. Ghost focus module

Download full size | View in the Article

Fig. 3. Ghost vision module

Download full size | View in the Article

Fig. 4. CViT-Net network structure diagram

Download full size | View in the Article

Fig. 5. Solar cell types

Download full size | View in the Article

Fig. 6. Solar cell defect detection process

Download full size | View in the Article

Fig. 7. Comparison chart of model accuracy compared to calculation amount and parameter amount

Download full size | View in the Article

Fig. 8. Visual positioning results under YOLOv5 detection framework

Download full size | View in the Article

输入分辨率	模块	输出分辨率	CViT-Net-S		CViT-Net-L
输入分辨率	模块	输出分辨率	输出通道数	重复	输出通道数	重复
224 × 224	Inception	224 × 224	12	1	24	1
224 × 224	G-C2F	112 × 112	24	1	48	2
112 × 112	G-C2F	56 × 56	48	2	96	2
56 × 56	G-ViT	28 × 28	96	2	192	2
28 × 28	G-ViT	14 × 14	192	4	384	4
14 × 14	G-ViT	7 × 7	384	2	768	2
7 × 7	池化	1× 1	384	1	768	1
1 × 1	Conv2d	1 × 1	384	1	768	1
1 × 1	Conv2d	1 × 1	K	1	K	1
Parameter			5.6 M		21.9 M
FLOPs			1.52 G		6.49 G

Table 1. CViT-Net model parameter table

View in the Article

名称	分类实验	检测实验
输入图像分辨率	224 × 224	640 × 640
训练轮数 (epoch)	100	300
批量尺寸 (Batch size)	40	8

Table 2. Classify and detect experimentally different parameter values

View in the Article

模型	测试分辨率	Precision/%	Recall/%	Accuracy/%	Parameter/M	FLOPs/G
ResNet50	224×224	93.07	95.06	94.38	23.5	4.11
DenseNet121	224×224	90.03	93.78	91.60	6.9	2.86
EfficientNet-B0	224×224	92.33	94.11	93.60	5.3	0.39
RegNet	224×224	93.25	95.17	94.40	24.5	6.52
MobileVit	224×224	91.48	95.28	93.10	5.6	1.44
MobileNetV3	224×224	92.78	93.78	92.20	5.4	0.23
ShuffleNetV2	224×224	91.42	94.78	93.00	3.4	0.13
GhostNet	224×224	91.56	95.46	93.20	3.9	2.45
CViT-Net-S	224×224	93.00	95.94	94.50	5.6	1.52
CViT-Net-L	224×224	93.70	96.28	95.10	21.9	6.49

Table 3. Comparison of advanced convolutional neural network algorithms

View in the Article

模型	Precision/%	Recall/%	Accuracy/%	Parameter/M	FLOPs/G
CViT-Net	79.86	80.25	86.78	4.59	4.2
CViT-Net+SE	80.74	80.58	87.68	5.60	1.53
CViT-Net+CBAM	87.0	87.6	92.24	5.63	1.54
CViT-Net+EMA	87.9	86.4	93.20	5.64	1.72
CViT-Net+CA	93.00	95.94	94.50	5.64	1.52

Table 4. Attention mechanism performance comparison

View in the Article

模型	G-C2F	G-ViT	CA	Parameter/M	FLOPs/G	Accuracy/%
Baseline	-	-	-	14.8	4.2	86.78
CViT-Net-S	√	-	-	8.9	1.35	92.15
CViT-Net-S	√	√	-	12.6	1.51	92.31
CViT-Net-S	√	√	√	5.6	1.52	94.50

Table 5. CViT-Net-S network ablation experiment

View in the Article

模型	mAP/%			mAP50/%
模型	隐裂	暗斑	瑕疵	mAP50/%
Two stage:
Faster R-CNN( ResNet50)	86.1	85.4	76.8	82.8
Cascade:R-CNN( ResNet50)	89.3	86.8	79.9	85
Sparse R-CNN( ResNet50)	74.5	75.4	64.1	71.3
FoveaBox( ResNet50)	88.3	85.2	61.8	78.5
One stage:
RetinaNet( ResNet50)	78.7	84.2	63.3	75.4
VFNet( ResNet50)	53.2	56.2	49.7	53
YOLOv5S	86.2	89.6	86.7	89.4
YOLOv6S	87.4	89.4	86.5	87.8
YOLOv7	80.8	86.7	81.2	82.9
YOLOv8S	86.9	88.1	86.0	87.0
YOLOX-S	88.1	88.8	87.2	88
PPYOLOE-S	87.7	89.9	84.5	87.4
YOLOv5(CViT-Net-S)	89.4	93.5	87.4	90.1
YOLOv5(CViT-Net-L)	89.5	93.6	87.5	90.2

Table 6. Experimental comparison of different target detection algorithms

View in the Article

检测框架	骨干网络	Precision/%	Recall/%	mAP/%	mAP50/%
YOLOv5	ResNet50	83.9	85.1	48.4	86.3
YOLOv5	DenseNet121	83.2	83.9	49.0	88.1
YOLOv5	EfficientNet	87.0	84.9	52.1	89.3
YOLOv5	RegNet	86.3	85.5	52.8	88.9
YOLOv5	MobileVit	82.9	82.0	49.9	87.4
YOLOv5	MobileNetV3	89.5	86.5	58.3	89.8
YOLOv5	ShuffleNetV2	83.7	80.4	48.6	86.8
YOLOv5	GhostNet	85.6	86.3	52.8	89.3
YOLOv5	CViT-Net-S	87.2	87.1	56.2	90.1
YOLOv5	CViT-Net-L	90.1	87.3	61.1	90.2

Table 7. YOLOv5 backbone network comparison experiment

Zhiyong Tao, Yan He, Sen Lin, Tingjun Yi, Yaosheng Zhang. Surface defect detection of solar cells using local and global feature fusion[J]. Opto-Electronic Engineering, 2024, 51(1): 230292-1

Download Citation

Tools

Save the article for my favorites

Paper Information