U-네트의 수용 영역 다양화를 이용한 혀 영역 분할
Tongue Segmentation Using the Receptive Field Diversification of U-net
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
본 논문에서는 U-네트에서 수용 영역을 다양화하여 기존의 모델보다 정확도가 개선된 새로운혀 영역 분할을 위한 딥러닝 모델을 제안한다. 수용 영역 다양화를 위하여 병렬 컨볼루션, 팽창된컨볼루션, 상수 채널 증가 등의 방법을 사용하였다. 제안된 딥러닝 모델에 대하여, 학습 영상과테스트 영상이 유사한 TestSet1과 그렇지 않은 TestSet2의 두 가지 테스트 데이터에 대해 혀 영역검출 실험을 진행하였다. 수용 영역이 다양화됨에 따라 혀 영역 분할 성능이 향상되는 것을 실험결과에서 확인할 수 있었다. 제안한 방법의 mIoU 값은 TestSet1의 경우 98.14%, TestSet2의 경우91.90%로 U-net, DeepTongue, TongueNet 등 기존 모델의 결과보다 높았다.
Abstract
In this paper, we propose a new deep learning model for tongue segmentation with improved accuracy compared to the existing model by diversifying the receptive field in the U-net. Methods such as parallel convolution, dilated convolution, and constant channel increase were used to diversify the receptive field. For the proposed deep learning model, a tongue region segmentation experiment was performed on two test datasets. The training image and the test image are similar in TestSet1 and they are not in TestSet2. Experimental results show that segmentation performance improved as the receptive field was diversified. The mIoU value of the proposed method was 98.14% for TestSet1 and 91.90% for TestSet2 which was higher than the result of existing models such as U-net, DeepTongue, and TongueNet.
참고문헌 (27)
- Marzia Hoque Tania, "Advances in automated tongue diagnosis techniques", Integrative Medicine Research, 8(1), pp.42~56 (2019), 한국한의학연구원[DOI]
- M. H. Subandia, "Prototyping digital tongue diagnosis system on roborealm and raspberry-pi", ZULFAQAR Journal of Defence Science, Engineering & Technology, 2(1), pp.24~33 (2019)
- Z. Li, "Tongue image segmentation via thresholding and clustering", International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI), pp.1~5 (2017)
- Jifeng Ning, "Automatic tongue image segmentation based on gradient vector flow and region merging", Neural Computing and Applications, 21(8), pp.1819~1826 (2012), Springer Science and Business Media LLC[DOI]
- J. Guo, "Adaptive active contour model based automatic tongue image segmentation", International Congress on Image and Signal Processing, Biomedical Engineering and Informatics, pp.1386~1390 (2016)
- Saparudin, "Tongue Segmentation Using Active Contour Model", International Conference on Electrical Engineering, Computer Science and Informatics, pp.1~5 (2016)
- Weixia Liu, "Tongue Image Segmentation via Thresholding and Gray Projection", KSII Transactions on Internet and Information Systems, 13(2), pp.945~961 (2019), 한국인터넷정보학회[DOI]
- P. Qu, "Automatic tongue image segmentation for traditional chinese medicine using deep neural network", Intelligent Computing Theories and Application, pp.247~259 (2017)[DOI]
- B. Lin, "Deeptongue: tongue segmentation via resnet", IEEE International Conference on Acoustics, Speech and Signal Processing, pp.1035~1039 (2018)
- Changen Zhou, "Tonguenet: Accurate Localization and Segmentation for Tongue Images Using Deep Neural Networks", IEEE Access, 7, pp.148779~148789 (2019), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- O. Ronneberger, "U-net: Convolutional Networks for Biomedical Image Segmentation", International Conference on Medical image computing and computer-assisted intervention, pp.234~241 (2015)
- F. Yu, "Multi-scale context aggregation by dilated convolutions", International Conference on Learning Representations (2016)
- A. Paszke, "ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation", arXiv preprint arXiv:1606.02147, ~ (2016)
- Evan Shelhamer, "Fully Convolutional Networks for Semantic Segmentation", IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(4), pp.640~651 (2017), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- A. Chaurasia, "LinkNet: Exploiting encoder representations for efficient semantic segmentation", IEEE Visual Communications and Image Processing, pp.1~4 (2017)[DOI]
- K. He, "Deep residual learning for image recognition", IEEE conference on computer vision and pattern recognition, pp.770~778 (2016)
- W. Liu, "Parsenet : Looking wider to see better", arXiv preprint arXiv:1506.04579v2, ~ (2015)
- H. Zhao, "Pyramid scene parsing network", IEEE Conference on Computer Vision and Pattern Recognition, pp.2881~2890 (2017)
- C. Peng, "Large kernel matters–improve semantic segmentation by global convolutional network", IEEE conference on computer vision and pattern recognition, pp.4353~4361 (2017)
- Eduardo Romera, "ERFNet: Efficient Residual Factorized ConvNet for Real-Time Semantic Segmentation", IEEE Transactions on Intelligent Transportation Systems, 19(1), pp.263~272 (2018), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- W. Xiang, "ThunderNet : A Turbo Unified Network for Real-Time Semantic Segmentation", IEEE Winter Conference on Applications of Computer Vision, pp.1789~1796 (2019)
- Mark Everingham, "The Pascal Visual Object Classes (VOC) Challenge", International Journal of Computer Vision, 88(2), pp.303~338 (2010), Springer Science and Business Media LLC[DOI]
- T. Y. Lin, "Microsoft COCO : Common objects in context", European conference on computer vision, pp.740~755 (2014)
- M. Cordts, "The cityscapes dataset for semantic urban scene understanding", IEEE Conference on Computer Vision and Pattern Recognition, pp.3213~3223 (2016)
- 진홍, "Enhancement of Tongue Segmentation by Using Data Augmentation", 한국정보전자통신기술학회 논문지, 13(5), pp.313~322 (2020), 한국정보전자통신기술학회
- Dan Shi, "An annotated dataset of tongue images supporting geriatric disease diagnosis", Data in Brief, 32, pp.106153~ (2020), Elsevier BV[DOI]
- G. H. Kim, "The development trends of tongue diagnosis system", The Magazine of the IEIE, 43(12), pp.35~43 (2016)
