Journal of Electrical Engineering and Technology

The Korean Institute of Electrical Engineers (대한전기학회)
권호 표지
DOI QR코드

DOI QR Code

A Study of Image Classification using HMC Method Applying CNN Ensemble in the Infrared Image

  • Received : 2017.05.15
  • Accepted : 2018.01.11
  • Published : 2018.05.01
Download PDF
⟨ Previous Next ⟩

Abstract

In the marine environment, many clutters have similar features with the marine targets due to the diverse changes of the air temperature, water temperature, various weather and seasons. Also, the clutters in the ground environment have similar features due to the same reason. In this paper, we proposed a robust Hybrid Machine Character (HMC) method to classify the targets from the clutters in the infrared images for the various environments. The proposed HMC method adopts human's multiple personality utilization and the CNN ensemble method to classify the targets in the ground and marine environments. This method uses an advantage of the each environmental training model. Experimental results demonstrate that the proposed method has better success rate to classify the targets and clutters than previously proposed CNN classification method.

Keywords

References

  1. H. Zhang, Z. Zhao and F. Xiao, "Robust Detection Method of Small Targets in Sea-Clutter via Improved Fast Clustering Segmentation," 10.1109/IHMSC.2016.236, pp. 123-126, 2016
  2. C. Yang, H. Liu, S. Liao and S. Wang, "Small target detection in infrared video sequence using robust dictionary learning," Infrared Physics & Technology, vol. 68, pp. 1-9, 2015 https://doi.org/10.1016/j.infrared.2014.09.039
  3. S. Qi, J. ma, H. Li, S. Zhang and J. Tian, "Infrared small target enhancement via phase spectrum of Quaternion Fourier Transform," Infrared Physics & Technology, vol. 62, pp. 50-58, 2014. https://doi.org/10.1016/j.infrared.2013.10.008
  4. Odegaard, N., Knapskog, A. O., Cochin, C., Louvigne, J. C. "Classification of ships using real and simulated data in a convolutional neural network," Rader Conference, 2016.
  5. Hiroshi Tasaka, "Everyone has multiple personality," Kobunsha Co. Japan, 2015.
  6. K. Simonyan and A. Zisserman, "Very deep convolutional networks for large-scale image recognition," arXiv, 2014.
  7. A. Krizhevsky, I. Sutskever and G. E. Hinton, "ImageNet Classification with Deep Convolution Neural Networks," In Pro. NIPS, 2012.
  8. S. Bell, P. Upchurch, N. Snavely and K. Bala, "Material recognition in the wild with the materials in context database," CoRR, abs/1412.0623, 2014.
  9. Tao Yang, "Application of Computational Verbs to Feeling Retrieval from Texts," International Journal of Computational Cognition, vol. 4, no. 3, pp. 28-45, 2006.