콘볼루션 신경망 (CNN)과 다양한 이미지 증강기법을 이용한 혀 영역 분할
Tongue Image Segmentation Using CNN and Various Image Augmentation Techniques
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
In Korean medicine, tongue diagnosis is one of the important diagnostic methods for diagnosing abnor- malities in the body. Representative features that are used in the tongue diagnosis include color, shape, texture, cracks, and tooth marks. When diagnosing a patient through these features, the diagnosis criteria may be different for each oriental medical doctor, and even the same person may have different diagnosis results depending on time and work environment. In order to overcome this problem, recent studies to automate and standardize tongue diag- nosis using machine learning are continuing and the basic process of such a machine learning-based tongue diagnosis system is tongue segmentation. In this paper, image data is augmented based on the main tongue features, and back- bones of various famous deep learning architecture models are used for automatic tongue segmentation. The exper- imental results show that the proposed augmentation technique improves the accuracy of tongue segmentation, and that automatic tongue segmentation can be performed with a high accuracy of 99.12%.
Abstract
In Korean medicine, tongue diagnosis is one of the important diagnostic methods for diagnosing abnor- malities in the body. Representative features that are used in the tongue diagnosis include color, shape, texture, cracks, and tooth marks. When diagnosing a patient through these features, the diagnosis criteria may be different for each oriental medical doctor, and even the same person may have different diagnosis results depending on time and work environment. In order to overcome this problem, recent studies to automate and standardize tongue diag- nosis using machine learning are continuing and the basic process of such a machine learning-based tongue diagnosis system is tongue segmentation. In this paper, image data is augmented based on the main tongue features, and back- bones of various famous deep learning architecture models are used for automatic tongue segmentation. The exper- imental results show that the proposed augmentation technique improves the accuracy of tongue segmentation, and that automatic tongue segmentation can be performed with a high accuracy of 99.12%.
참고문헌 (23)
- 손지희, "설진의 표준화를 위한 제언 : 설태 후박의 진단기준을 중심으로", 대한한방내과학회지, 33(1), pp.1~13 (2012), 대한한방내과학회[DOI]
- 신윤진, "舌診의 진단적 의의에 대한 문헌고찰", 한방안이비인후피부과학회지, 20(3), pp.118~126 (2007), 대한한방안이비인후피부과학회
- Kim GH, "설진의 과거와 미래 전망", The Magazine of the IEIE, 37(7), pp.62~71 (2010)
- 최민, "미각 영역별 설색 분석을 이용한 디지털 설진 시스템 개발", 한국정보통신학회논문지, 19(2), pp.428~434 (2015), 한국정보통신학회[DOI]
- 은성종, "설진 유효 분석을 위한 혀의 기하정보 추출 방법", 한국콘텐츠학회 논문지, 11(12), pp.522~532 (2011), 한국콘텐츠학회
- 박진웅, "ASM과 SVM을 이용한 설진 시스템 개발", 한국컴퓨터정보학회논문지, 18(4), pp.45~55 (2013), 한국컴퓨터정보학회
- 김근호, "설진 유효 영역 추출의 시스템적 접근 방법", 전자공학회논문지 - SC, 45(6), pp.123~131 (2008), 대한전자공학회
- 이민택, "영역 특징 학습을 이용한 혀의 자동 영역 분리 및 한의학적 설진 시스템", 한국정보통신학회논문지, 20(4), pp.826~832 (2016), 한국정보통신학회[DOI]
- 한영환, "능동 윤곽선 모델을 이용한 혀 영역의 검출", 재활복지공학회논문지, 10(2), pp.141~146 (2016), 한국재활복지공학회[DOI]
- Krizhevsky A, "Imagenet classification with deep convolutional neural networks", Advances in neural information processing systems, 25, pp.1097~1105 (2012)
- Simonyan K, "Very deep convolutional networks for large-scale image recognition", arXiv preprint arXiv:1409.1556. 2014 Sep 4, ~ (2014)
- Szegedy C, "Going deeper with convolutions", Proceedings of the IEEE conference on computer vision and pattern recognition, pp.1~9 (2015)
- He K, "Deep residual learning for image recognition", Proceedings of the IEEE conference on computer vision and pattern recognition, pp.770~778 (2016)
- Ronneberger O, "U-net: Convolutional networks for biomedical image segmentation", InInternational Conference on Medical image computing and computer-assisted intervention, pp.234~241 (2015), Springer
- Chaurasia A, "Linknet: Exploiting encoder representations for efficient semantic segmentation", 2017 IEEE Visual Communications and Image Processing (VCIP), pp.1~4 (2017), IEEE
- Zhao H, "Pyramid scene parsing network", Proceedings of the IEEE conference on computer vision and pattern recognition, pp.2881~2890 (2017)
- Oktay O, "Attention u-net: Learning where to look for the pancreas", arXiv preprint arXiv:1804.03999. 2018 Apr 11, ~ (2018)
- 이수정, "男子齒痕舌변증에 관한 임상적 고찰", Journal of Pharmacopuncture, 13(4), pp.91~108 (2010), 대한약침학회
- 박세욱, "중풍환자의 변증분형을 위한 설진에 관한 연구", 동의생리병리학회지, 22(1), pp.262~266 (2008), 한의병리학회
- 彭淸華, "望診", pp.247~ (2007), 청홍(지상사)
- Huang G, "Densely connected convolutional networks", Proceedings of the IEEE conference on computer vision and pattern recognition, pp.4700~4708 (2017)
- Szegedy C, "Inception-v4, inception-resnet and the impact of residual connections on learning", Thirty-first AAAI conference on artificial intelligence (2017)
- 박예랑, "내시경의 위암과 위궤양 영상을 이용한 합성곱 신경망 기반의 자동 분류 모델", 의공학회지, 41(2), pp.101~106 (2020), 대한의용생체공학회