Analysis of similar object classification performance of deep neural network-based object recognition technique

被引：0

作者：

Kim S.-H. ^{[1
]}

机构：

[1] Division of Aeronautics, Cheongju University

来源：

Journal of Institute of Control, Robotics and Systems | 2021年 / 27卷 / 11期

关键词：

Armored Fighting Vehicle; Deep Neural Networks; DenseNet; ResNet; Smart Factory;

D O I：

10.5302/J.ICROS.2021.21.0113

中图分类号：

学科分类号：

摘要：

In this study, deep neural networks were applied to a similar object classification method, and the classification performance was analyzed. For the similar object classification performance analysis, ResNet50 and DenseNet169 models, which are known to show similar behaviors, were selected. To verify the performance of these deep neural networks, a bolt recognition for smart factories and an armored fighting vehicle recognition were performed. In addition, image preprocessing methods to improve the similar object classification performance were proposed. The experimental results confirmed that appropriate image preprocessing methods should be applied according to the type of similar object to be classified. © ICROS 2021.

引用

页码：858 / 863

页数：5

共 13 条

[1]

Lehr J., Schluter M., Kruger J., Classification of similar objects of different sizes using a reference object by means of convolutional neural networks, 2019 24Th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA), (2019)

[2]

Choi K.H., Performance improvement of a deep learning-based object recognition using imitated red-green color blindness of camouflaged soldier images, Journal of the Korea Institute of Military Science and Technology, 23, 2, pp. 139-146, (2020)

[3]

He K., Zhang X., Ren S., Sun J., Deep residual learning for image recognition, Proceeding of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770-778, (2016)

[4]

Huang G., Liu Z., van Der Maaten L., Weinberger K.Q., Densely connected convolutional networks, Proceeding of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700-4708, (2017)

[5]

Krizhevsky A., Sutskever I., Hinton G.E., Imagenet classification with deep convolutional neural networks, Advances in Neural Information Processing Systems, pp. 1097-1105, (2012)

[6]

Very deep convolutional networks for large-scale image recognition, Arxiv Preprint Arxiv, 1409, (2014)

[7]

Szegedy C., Liu W., Jia Y., Sermanet P., Reed S., Anguelov D., Erhan D., Vanhoucke V., Rabinovich A., Going deeper with convolutions, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1-9, (2015)

[8]

Howard A.G., Zhu M., Chen B., Kalenichenko D., Wang W., Weyand T.M.H., Mobilenets: Efficient convolutional neural networks for mobile vision applications, Arxiv Preprint Arxiv, 1704, (2017)

[9]

Deng J., Dong W., Socher R., Li L.J., Li K., Fei-Fei L., Imagenet: A large-scale hierarchical image database, CVPR, (2009)

[10]

Krizhevsky A., Hinton G., Learning multiple layers of featues from tiny images, Tech Report, (2009)

← 1 2 →