Earticle

현재 위치 Home

Session 4: Technologies for Co-Prosperity

Is AI-based Hair Removal in Pet Skin Images Effective to Improve Skin Disease Detection?

첫 페이지 보기
  • 발행기관
    선문효정학술연구회 바로가기
  • 간행물
    선문효정학술연구회 학술대회 프로시딩 바로가기
  • 통권
    Proceedings of THE 4th INTERNATIONAL CONFERENCE OF HYOJEONG ACADEMY & 2024 INTERNATIONAL JOINT CONFERENCE (2024.08)바로가기
  • 페이지
    pp.101-105
  • 저자
    Kabin Prajapati, Youngchan Lee, Wonsang You
  • 언어
    영어(ENG)
  • URL
    https://www.earticle.net/Article/A489298

※ 기관로그인 시 무료 이용이 가능합니다.
※ 학술발표대회집, 워크숍 자료집 중 4페이지 이내 논문은 '요약'만 제공되는 경우가 있으니, 구매 전에 간행물명, 페이지 수 확인 부탁 드립니다.

4,000원

원문정보

초록

영어
Machine learning tools have been extensively exploited by dermatologists to determine the skin diseases in humans. However, less studies have been conducted in case of animals since they possess dense hairs in their skin. There are many researches on inpainting models to remove hair in the human skin images. We aim to determine the best model that can remove hairs in dermoscopic images of pet animals, specifically dogs and cats, and ultimately enhance the performance of skin disease detection. Three inpainting models, including BAT-Fill, EBAT, and DeepFillv2, were assessed to remove hairs from hairy raw skin images of pets. Those models were trained using human skin image datasets since paired data of hairy and hairless skin images are unavailable. The EBAT model exhibited the best qualitative performance in hair removal among those models. The inpainting models will be further examined to improve the accuracy for detecting skin diseases from pet skin images. It is obviously challenging due to the vulnerability of hair removal models to the heterogeneity of skin images over species while the available data of pet images are not sufficient to train them. We are pioneering to develop a robust model integrating hair removal and disease classification that can achieve superior performance over diverse species of animals.

목차

Abstract
1. Introduction
2. Materials and Methods
2.1. Image inpainting models for hair removal
2.2. Overall framework
3. Results
4. Conclusions
References

키워드

animal skin disease detection skin image hair removal deep learning image inpainting

저자

  • Kabin Prajapati [ AIIP Lab, Department of Information and Communication Engineering, Sun Moon University, Asan 31460, Korea ]
  • Youngchan Lee [ AIIP Lab, Department of Information and Communication Engineering, Sun Moon University, Asan 31460, Korea ]
  • Wonsang You [ AIIP Lab, Department of Information and Communication Engineering, Sun Moon University, Asan 31460, Korea ] Corresponding Author

참고문헌

자료제공 : 네이버학술정보

간행물 정보

발행기관

  • 발행기관명
    선문효정학술연구회 [Sun Moon Hyojeong Academy Society]
  • 설립연도
    2023
  • 분야
    복합학>학제간연구
  • 소개
    Journal of Hyojeong Academia aims to serve as a global platform where researchers and scholars of various disciplines can contribute ideas for our sustainable global community of Co‐existence, Co‐prosperity, and Co‐righteousness. The journal is a multidisciplinary, open‐access, internationally peer‐reviewed academic journal, and it invites all areas of research conducted in the spirit of post materialism including studies centering on God, studies unifying religions and sciences, and studies on all aspects of Co‐existence, Co‐prosperity, and Co‐righteousness.

간행물

  • 간행물명
    선문효정학술연구회 학술대회 프로시딩
  • 간기
    반년간
  • 수록기간
    2023~2026
  • 십진분류
    KDC 238 DDC 289

이 권호 내 다른 논문 / 선문효정학술연구회 학술대회 프로시딩 Proceedings of THE 4th INTERNATIONAL CONFERENCE OF HYOJEONG ACADEMY & 2024 INTERNATIONAL JOINT CONFERENCE

    피인용수 : 0건 (자료제공 : 네이버학술정보)

    함께 이용한 논문 이 논문을 다운로드한 분들이 이용한 다른 논문입니다.

      출처 : 네이버학술정보

        0개의 논문이 장바구니에 담겼습니다.

        페이지 저장
        소속기관 조회
        이용자님의 소속기관(단체)이 서비스에 가입되어 있는지 확인해 보십시오.
        기관회원에 소속되어 있는 이용자는 원문을 무료로 이용할 수 있습니다.