DOI QR코드

DOI QR Code

A Prediction System of Skin Pore Labeling Using CNN and Image Processing

합성곱 신경망 및 영상처리 기법을 활용한 피부 모공 등급 예측 시스템

  • Received : 2022.11.18
  • Accepted : 2022.12.22
  • Published : 2022.12.31

Abstract

In this paper, we propose a prediction system for skin pore labeling based on a CNN(Convolution Neural Network) model, where a data set is constructed by processing skin images taken by users, and a pore feature image is generated by the proposed image processing algorithm. The skin image data set was labeled for pore characteristics based on the visual classification criteria of skin beauty experts. The proposed image processing algorithm was applied to generate pore feature images from skin images and to train a CNN model that predicts pore feature ratings. The prediction results with pore features by the proposed CNN model is similar to experts visual classification results, where less learning time and higher prediction results were obtained than the results by the comparison model (Resnet-50). In this paper, we describe the proposed image processing algorithm and CNN model, the results of the prediction system and future research plans.

본 논문은 사용자들에 의해 촬영된 피부이미지를 가공하여 데이터 세트를 구축하고, 제안한 영상처리 기법에 의해 모공 특징이미지를 생성하여, CNN(Convolution Neural Network) 모델 기반의 모공 상태 등급 예측 시스템을 구현한다. 본 논문에서 활용하는 피부이미지 데이터 세트는, 피부미용 전문가의 육안 분류 기준에 근거하여, 모공 특징에 대한 등급을 라벨링 하였다. 제안한 영상처리 기법을 적용하여 피부이미지로 부터 모공 특징 이미지를 생성하고, 모공 특징 등급을 예측하는 CNN 모델의 학습을 진행하였다. 제안한 CNN 모델에 의한 모공 특징은 전문가의 육안 분류 결과와 유사한 예측 결과를 얻었으며, 비교 모델(Resnet-50)에 의한 결과보다 적은 학습시간과 높은 예측결과를 얻었다. 본 논문의 본론에서는 제안한 영상처리 기법과 CNN 적용의 결과에 대해 서술하며, 결론에서는 제안한 방법에 대한 결과와 향후 연구방안에 대해 서술한다.

Keywords

References

  1. J. K. Bae, "The Exploratory Study for the Appliftion of Artificial Intelligence in Smar Healthcare," Korean Association of Logos Management, vol.19, no.4, pp.180-197,
  2. N. Y. Park and et al., "Understanding the digital health care experience based on eHealth literach: Focusing on the Seoul citizens," Korea J Health Educ Promt, vol.39, no.4. pp.67-76, 2022. DOI: 10.14367/kjhep.2022.39.4.67
  3. K. H. Baek and E. N. Ha, "Mobile-based Digital Healthcare Platforms: Smart Wellness," Archives of Design Research(ADR), vol.34, no.1. pp.110-113, 2021. DOI: 10.15187/adr.2021.02.34.1.101
  4. H. G. Park and et al, "Image-Based Skin Diagnosis Using AI Technology Combine with Survey System for Review of integrated Skin Diagnosis Function," The Journal of the Convergence on Culture Technology(JCCT), vol.8, no.3. pp.463-468,
  5. H. G. Park and et al, "Image-Based Skin Diagnosis Using AI Technology Combine with Survey System for Review of integrated Skin Diagnosis Function," The Journal of the Convergence on Culture Technology(JCCT), vol.8, no.3. pp.463-468, 2022. DOI: 10.1007/s13555-022-00833-8
  6. K. K. Lee and et al, "Shooting Distance Adaptive Pore Extraction for Skin condition Estimateion," Journal of The Institute of Electronics and Information Engineers, vol.52, no.8. pp.106-114, 2015. DOI: 10.5573/ieie.2015.52.8.106