한국정보통신학회논문지 (Journal of the Korea Institute of Information and Communication Engineering)

  • 제21권1호
  • /
  • Pages.144-150
  • /
  • 2017
  • /
  • 2234-4772(pISSN)
  • /
  • 2288-4165(eISSN)
한국정보통신학회 (The Korea Institute of Information and Commucation Engineering)
권호 표지
DOI QR코드

DOI QR Code

소 부류 객체 분류를 위한 CNN기반 학습망 설계

Training Network Design Based on Convolution Neural Network for Object Classification in few class problem

  • Lim, Su-chang (Department of Computer Science, Sunchon National University) ;
  • Kim, Seung-Hyun (Department of Computer Science, Sunchon National University) ;
  • Kim, Yeon-Ho (Department of Computer Science, Sunchon National University) ;
  • Kim, Do-yeon (Department of Computer Engineering, Sunchon National University)
  • 투고 : 2016.08.02
  • 심사 : 2016.08.09
  • 발행 : 2017.01.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

최근 데이터의 지능적 처리 및 정확도 향상을 위해 딥러닝 기술이 응용되고 있다. 이 기술은 다층의 데이터 처리 레이어들로 구성된 계산 모델을 통해 이루어지는데, 이 모델은 여러 수준의 추상화를 거쳐 데이터의 표현을 학습한다. 딥러닝의 한 부류인 컨볼루션 신경망은 인간 행동 추정, 얼굴 인식, 이미지 분류, 음성 인식 같은 연구 분야에서 많이 활용되고 있다. 이미지 분류에 좋은 성능을 보여주는 컨볼루션 신경망은 깊은 학습망과 많은 부류를 이용하면 효과적으로 분류율을 높일수 있지만, 적은 부류의 데이터를 사용할 경우, 과적합 문제가 발생할 확률이 높아진다. 따라서 본 논문에서는 컨볼루션 신경망기반의 소부류의 분류을 위한 학습망을 제작하여 자체적으로 구축한 이미지 DB를 학습시키고, 객체를 분류하는 연구를 실험 하였으며, 1000개의 부류를 분류하기 위해 제작된 기존 공개된 망들과 비교 실험을 통해 기존 망보다 평균 7.06%이상의 상승된 분류율을 보여주었다.

Recently, deep learning is used for intelligent processing and accuracy improvement of data. It is formed calculation model composed of multi data processing layer that train the data representation through an abstraction of the various levels. A category of deep learning, convolution neural network is utilized in various research fields, which are human pose estimation, face recognition, image classification, speech recognition. When using the deep layer and lots of class, CNN that show a good performance on image classification obtain higher classification rate but occur the overfitting problem, when using a few data. So, we design the training network based on convolution neural network and trained our image data set for object classification in few class problem. The experiment show the higher classification rate of 7.06% in average than the previous networks designed to classify the object in 1000 class problem.

키워드

참고문헌

  1. Y. LeCun, Y. Bengio, and G. Hinton, "Deep learning," Nature, vol. 521, no.7553, pp. 436-444, May 2015. https://doi.org/10.1038/nature14539
  2. M. D. Zeiler, and R. Fergus, "Visualizing and understanding convolutional networks," in Proceedings of the 13th European Conference on Computer Vision, Zurich: CH, pp. 818-833, 2014.
  3. O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, and A.C. Berg, "ImageNet large scale visual recognition challenge," International Journal of Computer Vision, vol. 115, no. 3, pp. 211-252, Dec. 2015. https://doi.org/10.1007/s11263-015-0816-y
  4. K. Alex, S. Ilya, and H. Geoffrey, "ImageNet classification with deep convolutional neural networks," in Proceedings of Advances in Neural Information Processing System, Nevada: NV, pp. 1097-1105, 2012.
  5. C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich, "Going deeper with convolutions," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston: MA, pp. 1-9, 2015.
  6. S. Karen and Z. Andrew, "Very deep convolutional networks for large-scale image recognition," arXiv preprint arXiv:1409.1556, 2014.
  7. J.A.K. Suykens, and J. Vandewalle, "Least squares support vector machine classifiers," Neural processing letters 9, no.3, pp.293-300, 1999. https://doi.org/10.1023/A:1018628609742
  8. R. Gunnar, T. Onoda, and K. Muller, "Soft margins for adaBoost," Machine learning, vol. 42, no. 3, pp.287-320. 2001. https://doi.org/10.1023/A:1007618119488
  9. Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, "Gradient-based learning applied to document recognition," in Proceedings of the Institute of Electrical and Electronics Engineers, vol. 86, no.11, pp.2278-2324, 1998.
  10. Y. Jia, E. Shelhamer, J. Donahue, S. Karayev, J. Long, R. Girshick, S. Guadarrama, and T. Darrell, "Caffe: An open source convolutional architecture for fast feature embedding," in Proceedings of the 22nd ACM international conference on Multimedia, pp.675-678, 2014.

피인용 문헌

  1. Keras based CNN Model for Disease Extraction in Ultrasound Image vol.19, pp.10, 2018, https://doi.org/10.9728/dcs.2018.19.10.1975
  2. 병 인식 및 보증금 환불을 위한 분류 알고리즘 vol.21, pp.9, 2017, https://doi.org/10.6109/jkiice.2017.21.9.1744
  3. 지역적 가중치 파라미터 제거를 적용한 CNN 모델 압축 vol.22, pp.9, 2017, https://doi.org/10.6109/jkiice.2018.22.9.1165
  4. 컨볼루션 신경망 기반의 TW3 최대신장예측 시스템 vol.22, pp.10, 2017, https://doi.org/10.6109/jkiice.2018.22.10.1314
  5. Optimal hyperparameter tuning of convolutional neural networks based on the parameter-setting-free harmony search algorithm vol.172, pp.None, 2017, https://doi.org/10.1016/j.ijleo.2018.07.044
  6. Development of Automatic Classification Deep Learning System for Shine-muscat and Green-grape vol.22, pp.10, 2017, https://doi.org/10.9728/dcs.2021.22.10.1637