Journal of Advanced Navigation Technology (한국항행학회논문지)

The Korean Navigation Institute (한국항행학회)
권호 표지
DOI QR코드

DOI QR Code

Deep Learning-based Automatic Wrinkles Segmentation on Microscope Skin Images for Skin Diagnosis

피부진단을 위한 딥러닝 기반 피부 영상에서의 자동 주름 추출

  • Choi, Hyeon-yeong (ICT-CRC, Kumoh National Institute of Technology) ;
  • Ko, Jae-pil (Department of Computer Engineering, Kumoh National Institute of Technology)
  • 최현영 (금오공과대학교 ICT융합특성화연구센터) ;
  • 고재필 (금오공과대학교 컴퓨터공학과)
  • Received : 2020.03.13
  • Accepted : 2020.04.24
  • Published : 2020.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

Wrinkles are one of the main features of skin aging. Conventional image processing-based wrinkle detection is difficult to effectively cope with various skin images. In particular, Wrinkle extraction performance is significantly decreased when the wrinkles are not strong and similar to the surrounding skin. In this paper, deep learning is applied to extract wrinkles from microscopic skin images. In general, the microscope image is equipped with a wide-angle lens, so the brightness at the boundary area of the image is dark. In this paper, to solve this problem, the brightness of the skin image is estimated and corrected. In addition, We apply the structure of semantic segmentation network suitable for wrinkle extraction. The proposed method obtained an accuracy of 99.6% in test experiments on skin images collected in our laboratory.

주름은 피부의 노화도를 알 수 있는 주요한 특징 중의 하나이다. 기존의 영상처리기반 주름검출은 다양한 피부 영상에 효과적으로 대처하기 어렵다. 특히, 주름이 선명하지 않고 주변 피부와 유사한 경우 주름추출 성능은 급격히 떨어진다. 본 논문에서는 현미경 피부 영상에서 주름추출을 위해 딥러닝을 적용한다. 일반적으로 현미경 영상은 광각렌즈를 탑재하므로 영상 가장자리 영역의 밝기가 어둡다. 본 논문에서는 이를 해결하기 위해 피부 영상의 밝기를 추정하여 보정 한다. 또한, 주름추출에 적합한 의미분할 네트워크의 구조를 적용한다. 제안방법은 연구실에서 수집한 피부 영상에 대한 테스트 실험에서 99.6%의 정확도를 획득하였다.

Keywords

References

  1. Y. Bando, T. Kuratate, and T. Nishita, "A simple method for modeling wrinkles on human skin," in Proceedings of the 10th IEEE Pacific Conference on Computer Graphics and Applications, Beijing: China, pp. 166-175, 2002.
  2. T. Mclnerney and D. Terzopoulos, “Deformable models in medical image analysis : a survey,” Madical Image Analysis, Vol. 1, No. 2, pp. 91-108, 1996. https://doi.org/10.1016/S1361-8415(96)80007-7
  3. J. H. Rew, Y. H. Choi, H. J. Kim, and E. J. Hwang, "Skin aging estimation scheme based on lifestyle and dermoscopy image analysis," Applied Sciences (Switzerland), Vol. 9, No. 5, p. 1228, 2019. https://doi.org/10.3390/app9061228
  4. N. Batool and R. Chellappa, “Fast detection of facial wrinkles based on Gabor features using image morphology and geometric constraints,” Pattern Recognition, Vol. 48, No. 3, pp. 642-658, 2015. https://doi.org/10.1016/j.patcog.2014.08.003
  5. S. B. Lee and T. M. Kim, “A study on facial wrinkle detection using active appearance models,” Journal of Digital Convergence, Vol. 12, No. 7, pp. 239-245, 2014. https://doi.org/10.14400/JDC.2014.12.7.239
  6. M. W. Jo, A Study on the digital image processing algorithm for a non-contact type skin evaluation device, Master degree, Seoul National University, Korea, 2014.
  7. Y. H. Choi and I. J. Hwang, “A scheme of extracting age-related wrinkle feature and skin age based on dermoscopic images,” Journal of Institute of Korean Electrical and Electronics Engineers, Vol. 14, No. 4, pp. 332-338, 2010.
  8. F. J. W. Leong, M. Brady, and J. O. McGee, “Correction of uneven illumination (vignetting) in digital microscopy images,” Journal of Clinical Pathology, Vol. 56, No. 8, pp. 619-621, 2003. https://doi.org/10.1136/jcp.56.8.619
  9. O. Ronneberger, P. Fischer, and T. Brox, "U-Net: convolutional networks for biomedical image segmentation," Medical Image Computing and Computer Assisted Intervention, Vol. 9351, pp. 234-241, 2015.
  10. K. He, X. Zhang, S. Ren, and J. Sun, "Deep Residual Learning for Image Recognition," in 2016 IEEE International Conference on Computer Vision and Pattern Recognition, Las vegas: Nevada, pp. 770-778, 2016.
  11. D. P. Kingma and J. Ba, "Adam: a method for stochastic optimization," in Proceedings of the 3rd International Conference for Learning Representations, San Diego: CA, pp. 166-175, 2015.
  12. V. Nair and G. E. Hinton, "Rectified linear units improve restricted boltzmann machines," in Proceedings of the 27th International Conference on Machine Learning, Haifa: Israel, pp. 807-814 , 2010.
  13. K. He, X. Zhang, S. Ren, and J. Sun, "Delving deep into rectifiers: Surpassing human-level performance on imagenet classification," in 2015 IEEE International Conference on Computer Vision, Santiago: Chile, pp. 1026-1034, 2015.

Cited by

  1. WiFi 신호를 활용한 CNN 기반 사람 행동 인식 시스템 설계 및 구현 vol.25, pp.4, 2021, https://doi.org/10.12673/jant.2021.25.4.299