[논문]A Deep Learning Approach for Classification of Cloud Image Patches on Small Datasets

Phung, Van Hiep; Rhee, Eun Joo

doi:10.6109/jicce.2018.16.3.173

A Deep Learning Approach for Classification of Cloud Image Patches on Small Datasets 원문보기

Journal of information and communication convergence engineering, v.16 no.3, 2018년, pp.173 - 178

Phung, Van Hiep (Department of Computer Engineering, Hanbat National University) , Rhee, Eun Joo (Department of Computer Engineering, Hanbat National University)

Abstract ▼ AI-Helper

Accurate classification of cloud images is a challenging task. Almost all the existing methods rely on hand-crafted feature extraction. Their limitation is low discriminative power. In the recent years, deep learning with convolution neural networks (CNNs), which can auto extract features, has achieved promising results in many computer vision and image understanding fields. However, deep learning approaches usually need large datasets. This paper proposes a deep learning approach for classification of cloud image patches on small datasets. First, we design a suitable deep learning model for small datasets using a CNN, and then we apply data augmentation and dropout regularization techniques to increase the generalization of the model. The experiments for the proposed approach were performed on SWIMCAT small dataset with k-fold cross-validation. The experimental results demonstrated perfect classification accuracy for most classes on every fold, and confirmed both the high accuracy and the robustness of the proposed model.

주제어

표/그림 (8)

그림 Fig. 1. Sample images of each class from the SWIMCAT dataset.
그림 Fig. 2. Block diagram of a CNN.
표 Table 1. Augmentation parameters
그림 Fig. 3. Drop out concept visualization: (top) no dropout and (bottom) dropout 50% of the connections.
그림 Fig. 4. Schematic of 5-fold cross-validation.
표 Table 2. Architecture of our implemented convolutional network
표 Table 3. Experimental results
그림 Fig. 5. Confusion matrixes using the proposed approach.

AI 본문요약
AI-Helper

* AI 자동 식별 결과로 적합하지 않은 문장이 있을 수 있으니, 이용에 유의하시기 바랍니다.

문제 정의

This paper presented a deep learning solution for classification of cloud image patches on small datasets. For this research we used the dataset SWIMCAT, which consist of only 784 images.
This paper proposes a deep learning approach for classification of cloud images on small datasets. First, we design a deep learning model that includes both the feature extraction part and classification part using CNN, and then we apply two regularization techniques, data augmentation and dropout, to generalize our model.

제안 방법

This paper proposes a deep learning approach for classification of cloud images on small datasets. First, we design a deep learning model that includes both the feature extraction part and classification part using CNN, and then we apply two regularization techniques, data augmentation and dropout, to generalize our model. Our experiment is performed on the SWIMCAT dataset.
In this research, we used the SWIMCAT dataset which consists of only 784 image patches, which is a very small number for deep learning and makes it very easy to get overfitting. To overcome this problem we used two regularization methods.
In this study we did the data augmentation by applying random geometric transforms. The detailed configuration parameters of each augmentation method are shown in Table 1.
Theoretically, the larger number of convolutional layers (M is large) extracts more detailed features of input images; however, it needs a large amount of learning data. In this study, we selected less number of convolutional layers (M is small) and increased the generalization of our model by applying regularization techniques.
That is very small for deep learning applications, and it is very easy to get overfitting. To solve this problem, we designed a CNN model with enough convolutional layers for small datasets, and we applied two regularization methods, data augmentation and dropout to thoroughly treat the overfitting problem. In addition, the gold standard for the machine learning model, the k-fold cross-validation was also applied.

대상 데이터

This paper presented a deep learning solution for classification of cloud image patches on small datasets. For this research we used the dataset SWIMCAT, which consist of only 784 images. That is very small for deep learning applications, and it is very easy to get overfitting.
First, we design a deep learning model that includes both the feature extraction part and classification part using CNN, and then we apply two regularization techniques, data augmentation and dropout, to generalize our model. Our experiment is performed on the SWIMCAT dataset.

이론/모형

The hardware we used to implement the proposed network was a single PC Intel Core i5-7500 with the graphics processor NVIDIA GeForce GTX 1060 with 4 GB memory equipped. The software was developed using Python programming language based on Keras deep learning library[32] with back-end as TensorFlow [33].
In this research, we used the SWIMCAT dataset which consists of only 784 image patches, which is a very small number for deep learning and makes it very easy to get overfitting. To overcome this problem we used two regularization methods. The first augments data passed into the network for training, and the second modifies the network architecture.

성능/효과

In addition, the gold standard for the machine learning model, the k-fold cross-validation was also applied. Experimental results confirmed that we achieved perfect classification accuracy for all classes and all folds, with a minimum accuracy of 97.45% and maximum accuracies of 99.36%. These results prove that the proposed model not only achieves high accuracy but is also robust.
36%. These results prove that the proposed model not only achieves high accuracy but is also robust.

참고문헌 (33)

D. L. Hartmann, M. E. Ockert-bell, and M. L. Michelsen, "The effect of cloud type on Earth's energy balance: global analysis," Journal of Climate, vol. 5, no. 11, pp. 1281-1304, 1992. DOI: 10.1175/15200442(1992)005 2.0.CO;2.

상세보기
G. A. Isaac and R. A. Stuart, "Relationships between cloud type and amount, precipitation, and surface temperature in the Mackenzie River Valley-Beaufort Sea area," Journal of Climate, vol. 9, no. 8, pp. 1921-1941, 1996. DOI: 10.1175/1520-0442(1996)009 2.0.CO;2.

상세보기
F. Yuan, Y. H. Lee, and Y. S. Meng, "Comparison of radio-sounding profiles for cloud attenuation analysis in the tropical region," in Proceedings of IEEE International Symposium on Antennas and Propagation, Memphis, TN, pp. 259-260, 2004. DOI: 10.1109/APS.2014.6904461.
Y. Liu, J. R. Key, and X. Wang, "The influence of changes in cloud cover on recent surface temperature trends in the Arctic," Journal of Climate, vol. 21, no. 4, pp. 705-715, 2008. DOI: 10.1175/2007JCLI1681.1.

상세보기
F. Cui, R. Ju, Y. Ding, H. Ding, and X. Cheon, "Prediction of regional global horizontal irradiance combining ground-based cloud observation and numerical weather prediction," Advanced Material Research, vol. 1073-1076, pp. 388-394, 2014. DOI: 10.4028/www.scientific.net/amr.1073-1076.388.

상세보기
M. C. Naud, J. F. Booth, and A. D. Del Genio, "The relationship between boundary layer stability and cloud cover in the post-coldfrontal region," Journal of Climate, vol. 29, no. 22, pp. 8129-8149, 2016. DOI: 10.1175/JCLI-D-15-0700.1.

상세보기
D. Pages, J. Calbo, J. A. Gonzalez, and J. Badosa, "Comparison of several ground-based cloud detection techniques," in Abstracts of European Geophysical Society XXVII Assembly, Nice, France, pp. 269-299, 2002.
K. A. Buch and C. H. Sun "Cloud classification using whole-sky imager data," in Proceedings of the 9th Symposium on Meteorological Observations and Instrumentation, Charlotte, NC, 1995.
M. Singh and M. Glennen, "Automated ground-based cloud recognition," Pattern Analysis and Applications, vol. 8, no. 3, pp. 258-271, 2005. DOI: 10.1007/s10044-005-0007-5.

상세보기
J. Calbo and J. Sabburg, "Feature extraction from whole-sky groundbased images for cloud-type recognition," Journal of Atmospheric and Oceanic Technology, vol. 25, no. 1, pp. 3-14, 2008. DOI: 10.1175/2007JTECHA959.1.

상세보기
A. Heinle, A. Macke, and A. Srivastav, "Automatic cloud classification of whole sky images," Atmospheric Measurement Techniques, vol. 3, no. 3, pp. 557-567, 2010. DOI: 10.5194/amt-3-557-2010.

상세보기
S. Liu, C. Wang, B. Xiao, Z. Zhang, and Y. Shao, "Illuminationinvariant completed LTP descriptor for cloud classification," in Proceedings of the 5th International Congress on Image Signal Processing (CISP), Chongqing, China, pp. 449-453, 2012. DOI: 10.1109/CISP.2012.6469765.
L. Liu, X. Sun, F. Chen, S. Zhao, and T. Gao, "Cloud classification based on structure features of infrared images," Journal of Atmospheric and Oceanic Technology, vo. 28, no. 3, pp. 410-417, 2011. DOI: 10.1175/2010JTECHA1385.1.

상세보기
S. Liu, C. Wang, B. Xiao, Z. Zhang, and Y. Shao, "Salient local binary pattern for ground-based cloud classification," Acta Meteorologica Sinica, vo. 27, no. 2, pp. 211-220, 2013. DOI: 10.1007/s13351-013-0206-8.

상세보기
S. Liu, Z. Zhang, and X. Mei, "Ground-based cloud classification using weighted local binary patterns," Journal of Applied Remote Sensing, vol. 9, no. 1, article no. 095062, 2015. DOI: 10.1117/1.JRS.9.095062.

상세보기
S. Dev, Y. H. Lee, and S. Winkler, "Categorization of cloud image patches using an improved texton-based approach," in Proceedings of IEEE International Conference on Image Processing (ICIP), Quebec City, Canada, pp. 422-426, 2015. DOI: 10.1109/ICIP.2015.7350833.
Q. Luo, Y. Meng, L. Liu, X. Zhao, and Z. Zhou, "Cloud classification of ground-based infrared images combining manifold and texture features," Atmospheric Measurement Techniques, 2017. DOI: 10.5194/amt-2017-402.
J. Gan, W. Lu, Q. Li, Z. Zhang, J. Yang, Y. Ma, and W. Yao, "Cloud type classification of total-sky images using duplex norm-bounded sparse coding," IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 10, no. 7, pp. 3360-3372, 2017. DOI: 10.1109/JSTARS.2017.2669206.

상세보기
A. Krizhevsky, I. Sutskever, and G. E. Hinton, "ImageNet classification with deep convolutional neural networks," Advances in Neural Information Processing System, vol. 25, pp. 1097-1105, 2012.
C. Shi, C. Wang, Y. Wang, and B. Xiao, "Deep convolutional activations-based features for ground-based cloud classification," IEEE Geoscience and Remote Sensing Letters, vol. 14, no. 6, pp. 816-820, 2017. DOI: 10.1109/LGRS.2017.2681658.

상세보기
L. Ye, Z. Cao, Y. Xiao, and W. Li, "Ground-based cloud image categorization using deep convolutional visual features," in Proceeding of 2015 IEEE International Conference on Image Processing, Quebec City, QC, Canada, pp. 4808-4812, 2015. DOI: 10.1109/ICIP.2015.7351720.
L. Ye, Z. Cao, and Y. Xiao, "DeepCloud: ground-based cloud image categorization using deep convolutional features," IEEE Transactions on Geoscience and Remote Sensing, vol. 55, no. 10, pp. 5729-5740, 2017. DOI: 10.1109/TGRS.2017.2712809.

상세보기
Z. Zhang, D. Li, S. Liu, B. Xiao, and X. Cao, "Multi-view groundbased cloud recognition by transferring deep visual information," Applied Sciences, vol. 8, no. 5, article no. 748, 2018. DOI: 10.3390/app8050748.

상세보기
S. Dev, F. M. Savoy, Y. H. Lee, and S. Winkler, "WAHRSIS: a lowcost high-resolution whole sky imager with near-infrared capabilities," in Infrared Imaging Systems: Design, Analysis, Modeling, and Testing XXV (Vol. 9071). Bellingham, WA: International Society for Optics and Photonics, 2014. DOI: 10.1117/12.2052982.
Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, "Gradient-based learning applied to document recognition," Proceedings of the IEEE, vol. 86, no. 11, pp. 2278-2324, 1998. DOI: 10.1109/5.726791.

상세보기
K. Fukushima, "Neocognitron: a self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position," Biological Cybernetics, vol. 36, no. 4, pp. 193-202, 1980. DOI: 10.1007/BF00344251.

상세보기
J. Deng, A. Berg, S. Satheesh, H. Su, A. Khosla, and L. Fei-Fei, "ImageNet large scale visual recognition competition 2012," 2012 [Internet], Available: www.image-net.org/challenges/LSVRC/2012/.
J. Deng, W. Dong, R. Socher, L. J. Li, K. Li, and L. Fei-Fei, "Image-Net: a large-scale hierarchical image database," in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 248-255, 2009. DOI: 10.1109/CVPR.2009.5206848.
L. Hertel, E. Barth, T. Kaster, and T. Martinetz, "Deep convolutional neural networks as generic feature extractors," in Proceedings of 2015 International Joint Conference on Neural Networks (IJCNN), Killarney, Ireland, pp. 1-4, 2015. DOI: 10.1109/IJCNN.2015.7280683.
A. Karpathy, "Convolutional Networks," [Internet], Available: http://cs231n.github.io/convolutional-networks/.
H. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, "Dropout: a simple way to prevent neural networks from overfitting," The Journal of Machine Learning Research, vol. 15, no. 1, pp. 1929-1958, 2014.
Keras: The Python Deep Learning library [Internet], Available: https://keras.io/.
M. Abadi, A. Agarwal, P. Barham, E. Brevdo, Z. Chen, C. Citro, et al., "TensorFlow: large-scale machine learning on heterogeneous distributed systems," 2016 [Internet], Available: https://arxiv.org/abs/1603.04467.

저자의 다른 논문 :

표제어: PCR

동의어: Packet Collision Rate

용어 설명 출처 목록 (6)

용어 설명: PCR은 세균 특이성이 있는 primer를 이용하여 적은 수의 세균이 있을지라도 쉽게 검출할 수 있는 유용한 방법이며, 이를 이용하여 구강 내 치면세균막이나 타액에서 직접 세균을 검출할 수 있게 되었다[8].

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증