Journal of the Korean Society of Industry Convergence (한국산업융합학회 논문집)

The Korean Society of Industry Convergence (한국산업융합학회)
권호 표지
DOI QR코드

DOI QR Code

Feature Extraction Using Convolutional Neural Networks for Random Translation

랜덤 변환에 대한 컨볼루션 뉴럴 네트워크를 이용한 특징 추출

  • 진태석 (동서대학교 메카트로닉스공학과)
  • Received : 2020.05.01
  • Accepted : 2020.06.08
  • Published : 2020.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

Deep learning methods have been effectively used to provide great improvement in various research fields such as machine learning, image processing and computer vision. One of the most frequently used deep learning methods in image processing is the convolutional neural networks. Compared to the traditional artificial neural networks, convolutional neural networks do not use the predefined kernels, but instead they learn data specific kernels. This property makes them to be used as feature extractors as well. In this study, we compared the quality of CNN features for traditional texture feature extraction methods. Experimental results demonstrate the superiority of the CNN features. Additionally, the recognition process and result of a pioneering CNN on MNIST database are presented.

Keywords

References

  1. D. Rumelhart, G. Hintont, and R. Williams, "Learning representations by back-propagating errors," Nature, pp.533-536, (1986).
  2. A. Krizhevsky, I. Sutskever, and G. E. Hinton, "Imagenet classication with deep convolutional neural networks," Advances in Neural Information Processing Systems 25, pp.1106-1114, (2012).
  3. G. E. Hinton, N. Srivastava, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, "Improving neural networks by preventing co-adaptation of feature detectors," CoRR, vol. abs/1207.0580, (2012).
  4. N. Dalal, and B. Triggs, "Histograms of oriented gradients for human detection," International Conference on Computer Vision & Pattern Recognition, vol.2, pp.886-893, (2005).
  5. K.J Choi, "Optimization of Posture for Humanoid Robot Using Artificial Intelligence, "Journal of the Korean Society of Industry Convergence, vol.22, no.2, pp.87-93, (2019). https://doi.org/10.21289/KSIC.2019.22.2.87
  6. J.P. Lee, J.W. Lee, G.H. Lee, "A Scheme of Security Drone Convergence Service using Cam-Shift Algorithm," Journal of the Korean Society of Industry Convergence, vol.7, no.5, pp.629-34, (2016).
  7. S.J. Hong, Y.H. Cho," A System Implementation Based on Matlab and NET for Recognizing Facial Expression, "Conference of the Korean Society of Industry Convergence, pp.7-12, (2009).
  8. Y.J. Kim, H.J. Kim, J.Y. Han, S. Lee, "Classification of Tire Tread Wear Using Accelerometer Signals through an Artificial Neural Network," Journal of the Korean Society of Industry Convergence, vol.23, no.2, pp.163- 171, (2020).