2020
DOI: 10.1007/s11042-020-09152-6
|View full text |Cite
|
Sign up to set email alerts
|

An improved MobileNet-SSD algorithm for automatic defect detection on vehicle body paint

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
8
0
1

Year Published

2020
2020
2024
2024

Publication Types

Select...
6
2
1

Relationship

0
9

Authors

Journals

citations
Cited by 34 publications
(13 citation statements)
references
References 25 publications
0
8
0
1
Order By: Relevance
“…Through experiments, it can be seen that Adam optimizer has very good comprehensive performance, and can improve the accuracy and convergence speed of the model by combining with the migration learning algorithm. Design experiments, comparing the optimization algorithm with the traditional MobileNet model, we can see that the improved algorithm can better complete the task and improve the recognition accuracy, and there are many improvements in all aspects [9]. The literature describes the characteristics of different detection algorithms,a convolutional neural network is proposed to optimize the algorithm to complete the construction of tensor ow network system,which completes the programming in pycharm environment and the hardware implementation based on Xavier module [10].…”
Section: Relevant Workmentioning
confidence: 99%
“…Through experiments, it can be seen that Adam optimizer has very good comprehensive performance, and can improve the accuracy and convergence speed of the model by combining with the migration learning algorithm. Design experiments, comparing the optimization algorithm with the traditional MobileNet model, we can see that the improved algorithm can better complete the task and improve the recognition accuracy, and there are many improvements in all aspects [9]. The literature describes the characteristics of different detection algorithms,a convolutional neural network is proposed to optimize the algorithm to complete the construction of tensor ow network system,which completes the programming in pycharm environment and the hardware implementation based on Xavier module [10].…”
Section: Relevant Workmentioning
confidence: 99%
“…When the IoU threshold was 0.5, the average accuracy reached 93.7%. Zhang et al [22] substituted MobileNet for vgg16 network in the SSD model, which not only optimizes the delay but also performs high-precision detection. They proposed an aspect ratio method suitable for paint images, which can detect six traditional car body paint film defects, with an accuracy of over 95%.…”
Section: Related Workmentioning
confidence: 99%
“…Zhang et al(2020) [1] proposed an improved MobileNet-SSD algorithm that was able to detect six conventional body paint defects with more than 95% accuracy. However, this method lacks high-level feature mapping semantics for small target prediction, resulting in insufficient accuracy of small target detection.…”
Section: Introductionmentioning
confidence: 99%