반도체디스플레이기술학회지 (Journal of the Semiconductor & Display Technology)

한국반도체디스플레이기술학회 (The Korean Society Of Semiconductor & Display Technology)
권호 표지

CNN기초로 세 가지 방법을 이용한 감정 표정 비교분석

Comparative Analysis for Emotion Expression Using Three Methods Based by CNN

  • 양창희 (단국대학교 전자전기공학부) ;
  • 박규섭 (단국대학교 전자전기공학부) ;
  • 김영섭 (단국대학교 전자전기공학부) ;
  • 이용환 (원광대학교 디지털콘텐츠공학화)
  • Yang, Chang Hee (Department of Electronic and Electrical Engineering, Dankook University) ;
  • Park, Kyu Sub (Department of Electronic and Electrical Engineering, Dankook University) ;
  • Kim, Young Seop (Department of Electronic and Electrical Engineering, Dankook University) ;
  • Lee, Yong Hwan (Department of Digital Contents, Wonkwang University)
  • 투고 : 2020.11.30
  • 심사 : 2020.12.08
  • 발행 : 2020.12.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

CNN's technologies that represent emotional detection include primitive CNN algorithms, deployment normalization, and drop-off. We present the methods and data of the three experiments in this paper. The training database and the test database are set up differently. The first experiment is to extract emotions using Batch Normalization, which complemented the shortcomings of distribution. The second experiment is to extract emotions using Dropout, which is used for rapid computation. The third experiment uses CNN using convolution and maxpooling. All three results show a low detection rate, To supplement these problems, We will develop a deep learning algorithm using feature extraction method specialized in image processing field.

키워드

참고문헌

  1. Warren C., Ghassan H., "n -SIFT: n -Dimensional Scale Invariant Feature Transform," IEEE, pp, 2012 - 2021, 05 June 2009.
  2. Herbert B., Andreas E., Tinne T., Luc Van G., "Speeded-Up Robust Features (SURF)," ScienceDirect, pp, 246-359, June 2008.
  3. Dalal N., Triggs B., "Histograms of oriented gradients for human detection," IEEE, 25 July 2005.
  4. Deniz O., Bueno G., Salido J., F.De la T., "Face recognition using Histograms of Oriented Gradients," ScienceDirect, 20 January 2011.
  5. Harihara Santosh D., Gopala Krishna Mohan P., "Improved Face Recognition Rate Using HOG Features and SVM Classifier," IOSR-JECE, pp 34-44, Jul-aug 2016.
  6. Ronan C., Samy B., "Links between perceptrons, MLPs and SVMs," Proceedings of the twenty-first international conference on Machine learning, July 2004.
  7. Philip C.L., Chun-Yang Z., "Fuzzy Restricted Boltzmann Machine for the Enhancement of Deep Learning," IEEE, 24 February 2015.
  8. Geoffrey E. Hinton, "Deep belief networks," Scholarpedia, 4(5):5947., 2009. https://doi.org/10.4249/scholarpedia.5947
  9. Ahmed Ali Mohammed A., Hai T., Mohammed Ahmed T., "Review of deep convolution neural network in image classification," IEEE, 11 January 2018.
  10. loffe S., Szegedy C., "Batch Normalization : Accelerating Deep Network Training by Reducing Internal Covariance Shift," NIPS, 2 Mar 2015.
  11. Alvin P., Dae-Ki K., "Biased Dropout and Crossmap Dropout: Learning towards effective Dropout regularization in convolutional neural network," SienceDirect, pp.60-67, August 2018.
  12. Grosse R., "Lecture 15 : Exploding and Vanishing Gradients", University of Toronto Computer Science, 2017.
  13. "Challenges in Representation Learning: Facial Expression Recognition Challenge," Kaggle, 2013.
  14. "IMPA-FACE3D," visgraf.impa.br., Retrieved 2018-03-08.
  15. https://opencv-python-tutroals.readthedocs.io/en/latest/py_tutorials/py_objdetect/py_face_detection/py_face_detection.html.
  16. Octavio A., Matias V., Paul P., "Real-time Convolution Neural Networks for emotion and Gender Classification," Cornell University, 20 Oct 2017.
  17. Kim H.I., Moon J.Y., Park J.Y.,"Research Trends for Deep Learning-Based High-Performance Face Recognition Technology", KoreaSience, 2018.
  18. Kim G.T., Lee Y.H., Kim Y.,S.,"Analysis of Feature Algorithms Based on Deep Learning", JSDT, June 2020.