簡易檢索 / 詳目顯示

回結果列表
研究生： 朱成宗
Chu, Cheng-Tsung
論文名稱： 使用影像處理與機器學習方法測量下肢水腫
An Image Processing and Machine Learning Method for Measuring Lower Limb Edema
指導教授： 侯廷偉
Hou, Ting-Wei
學位類別： 碩士
Master
系所名稱： 工學院 - 工程科學系碩士在職專班
Department of Engineering Science (on the job class)
論文出版年： 2021
畢業學年度： 109
語文別： 中文
論文頁數： 79
中文關鍵詞： 下肢水腫 、凹陷性水腫分級 、影像處理 、機器學習 、水腫自動檢測應用
外文關鍵詞： Lower limb edema, Grading pitting edema, Image processing, Machine learning, Edema automatic detection application
相關次數： 點閱：140  下載：4 
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

    • 本論文建立一套「水腫自動檢測應用系統」可直接透過手機鏡頭拍攝下肢水腫影片，系統自動以影像處理的技術進行分類判讀後，即時回報該手機並顯示其水腫嚴重程度。本研究有5位自願參與者，共收集37部拍攝影片完成所有實驗的任務。同時本研究考量拍攝個案對象之BMI值及外在環境因素的多元性變化; 也使用了這些影片讓應用系統進行了自動檢測。研究結果顯示，透過影像處理方法將圖像進行Canny邊緣檢測、SSIM指標值、HOG特徵描述及邏輯回歸分類器整合應用，以目前系統訓練出的檢測模型達到89.2%精確度。

    An automatic detection application system for lower limb edema is designed and implemented in this research. It uses the camera of a mobile phone to directly take videos of the lower limb edema and analyze the taken video to check if there is edema. After the video is taken, the video is sent to a server which performs automatic classification by image processing and generates a report. The report of the grading pitting edema is sent immediately back to the mobile phone to show to the user.
    This study recruited 5 voluntary participants to collect a total of 37 videos for the experiment. The research took the diverse variability of the volunteers, such as BMI values, and environmental factors into consideration. The detection of the system is performed automatically. The proposed system adopted the image processing techniques includes Canny edge detection, SSIM index values, HOG feature description and logistic regression classifier. The precision of the proposed model is 89.2%.

    摘要 I Extended Abstract II 誌謝 VIII 目錄 IX 表目錄 XII 圖目錄 XIV 第一章、緒論 1 1-1 研究背景 1 1-2 研究動機 1 1-3 研究目的 2 1-4 實作範圍 2 1-5 論文架構 3 第二章、相關文獻探討 4 2-1 相關文獻的研究比較 4 2-2 影像處理基礎觀念 10 2-3 影像分析方法 11 2-4 影像降低噪點方法 13 2-5 高斯濾波器( Gaussian Filter ) 13 2-6 大津演算法(Otsu’s method) 16 2-7 邊緣檢測方法 17 2-8 結構相似性指標(Structural Similarity Index，SSIM Index) 19 2-9 方向梯度直方圖( Histogram of Oriented Gradient，HOG) 21 2-10 機器學習分類器( Machine Learning Classifier ) 24 第三章、研究方法 26 3-1 手機應用程式 26 3-1-1 使用案例圖(Use Case Diagram) 26 3-1-2 使用者介面(User Interface) 28 3-1-3 應用程式整合性功能 29 3-2 自動檢測模型 30 3-2-1 自動檢測模型基礎架構 30 3-2-2 食指移開物件偵測 31 3-3 有無凹陷狀態分類判定 33 3-3-1 灰階化搭配結構相似指標值(Gray Image-SSIM) 33 3-3-2 二值化搭配結構相似指標值(Binary Image-SSIM) 35 3-3-3 方向梯度直方圖搭配機器學習分類器(HOG-ML Classifier) 39 3-4 整體系統架構 43 3-4-1 系統基礎架構說明 43 3-4-2 應用系統環境與架構 46 第四章、實驗結果與討論 49 4-1 支持向量機(Support Vector Machine,SVM) 51 4-2 樸素貝葉斯(Naive Bayes,NB) 52 4-3 邏輯回歸(Logistic Regression,LR) 52 4-4 隨機森林(Random Forest,RF) 53 4-5 決策樹(Decision Tree,DT) 54 4-6 支持向量機(Support Vector Machine,SVM) on (Dent0~4+) 56 4-7 樸素貝葉斯(Naive Bayes,NB) on (Dent0~4+) 57 4-8 邏輯回歸(Logistic Regression,LR) on (Dent0~4+) 58 4-9 隨機森林(Random Forest,RF) on (Dent0~4+) 59 4-10 決策樹 ( Decision Tree, DT )on (Dent0~4+) 60 4-11 驗證案例的實驗結果 61 4-12 實驗結果探討 62 第五章、結論與未來展望 64 5-1 研究結論 64 5-2 研究之創新性與預期影響性 64 5-3 研究貢獻及未來期望 65 參考文獻 67 附錄 A 71 附錄 B 74 附錄 C 77

    [1] R. W. S. Henry M. Seidel, Jane W. Ball, Joyce E. Dains, John A. Flynn, Barry S.
    Solomon, Mosby's Guide to Physical Examination, 7th Edition ,
    ISBN 10:0323055702 / ISBN 13:9780323055703. 2010.
    [2] WHO, "WHO: Top 10 Causes of Death (2015)," 2015. [Online]. Available:
    http://www.who.int/mediacentre/factsheets/fs310/en/. , last retieved:
    December 9,2020.
    [3] C. S. Lam et al., "Regional and ethnic differences among patients with heart failure
    in Asia: the Asian sudden cardiac death in heart failure registry,", European Heart
    Journal, vol. 37, no. 41, pp. 3141-3153, Nov 1 2016, doi: 10.1093/eurheartj/ehw331.
    [4] 衛福部, "108年國人死因統計結果," 2019. [Online]. Available:
    https://www.mohw.gov.tw/cp-16-54482-1.html , last retieved : June 16,2020.
    [5] 衛福部, "2017年衛生福利品質指標報告," 2018. [Online]. Available:
    https://www.mohw.gov.tw/cp-3232-18296-1.html , last retieved : August 26, 2019.
    [6] 衛生福利部中央健康保險署, "全民健康保險急性後期整合照護計畫_心臟衰竭
    106 年版," 2017.
    [7] Wikipedia, "Information and communications technology," [Online]. Available:
    https://en.wikipedia.org/wiki/Information_and_communications_technology ,
    last retieved:December 12,2020.
    [8] J. Chen and T. Mao, "Camera-based peripheral edema measurement using machine
    learning," 2018 IEEE International Conference on Healthcare Informatics (ICHI),
    4-7 June 2018, pp. 457-458, DOI: 10.1109/ICHI.2018.00101.
    [9] K. Williams, M. Han, S. Hardin, S. George, and J. Yao, "AERO: An objective
    peripheral edema measurement device," 2018 40th Annual International Conference
    of the IEEE Engineering in Medicine and Biology Society (EMBC) , July 2018 pp.
    5914-5917. DOI: 10.1109/EMBC.2018.8513657
    [10] S. M. George, B. D. Langley, E. M. B. Weaver, S. R. Hardin, and Y. Jianchu,
    "Design of peripheral edema measurement device for home use,"2016 38th Annual
    International Conference of the IEEE Engineering in Medicine and Biology Society
    (EMBC) , 16-20 Aug. 2016, pp. 4387-4390. DOI: 10.1109/EMBC.2016.7591699
    [11] S.-C. Company, "Siren Socks智慧襪," 2018. [Online]. Available:
    https://siren.care/. , last retieved:November 10,2020.
    [12] O. Company, "SurroSense Rx智慧運動鞋," 2013. [Online]. Available:
    http://www.mobihealthnews.com/27307/surrosense-rx-foot-sensor-hits-market-
    aims-to-prevent-diabetic-ulcers. , last retieved:November 13,2013.
    [13] C. Yahathugoda et al., "Use of a novel portable three-dimensional imaging system
    to measure limb volume and circumference in patients with filarial lymphedema,"
    , American Journal of Tropical Medicine and Hygiene, vol. 97, no. 6, pp. 1836-1842, Dec 2017, doi: 10.4269/ajtmh.17-0504.
    [14] R. M. M. Creber, A. Myers, P. Goyal, and Z. Kostic, "Deep learning method
    for video-based data to classify peripheral edema grades," Journal of Cardiac Failure,
    Abstract vol. 25, no. 8, pp. S103-S103, 08/01/August 2019 2019, doi:
    10.1016/j.cardfail.2019.07.295.
    [15] 維基百科, "電腦視覺(Computer vision),". [Online]. Available:
    https://zh.wikipedia.org/wiki/電腦視覺. , last retieved:September 19,2020.
    [16] Wikipedia, "Machine vision," [Online]. Available:
    https://en.wikipedia.org/wiki/Machine_vision. , last retieved:October 15,2020.
    [17] 維基百科, "影像處理," 2019年8月29日. [Online]. Available:
    https://zh.wikipedia.org/wiki/影像處理. , last retieved:August 29,2019.
    [18] 維基百科, "影像降噪," [Online]. Available:
    https://zh.wikipedia.org/wiki/%E5%BD%B1%E5%83%8F%E9%99%8D%E5%99%AA
    , last retieved:July 22,2020.
    [19] Wikipedia, "Gaussian filter," [Online]. Available:
    https://en.wikipedia.org/wiki/Gaussian_filter. , last retieved:October 14,2020.
    [20] S. P. Bob Fisher, Ashley Walker and Erik Wolfart, "Gaussian smoothing," 1994.
    [Online]. Available: https://homepages.inf.ed.ac.uk/rbf/HIPR2/gsmooth.htm. ,
    last retieved: November 9,2006.
    [21] Wikipedia, "Otsu’s method," [Online]. Available:
    https://en.wikipedia.org/wiki/Otsu%27s_method. , last retieved:October 13,2020.
    [22] OpenCV, "Canny edge detection," [Online]. Available:
    https://docs.opencv.org/master/da/d22/tutorial_py_canny.html. , last retieved:
    December 4,2020.
    [23] Wikipedia, "Canny edge detector," [Online]. Available:
    https://en.wikipedia.org/wiki/Canny_edge_detector. , last retieved:November 26,2020.
    [24] Wikipedia, "Structural similarity index measure (SSIM)," [Online]. Available:
    https://en.wikipedia.org/wiki/Structural_similarity. , last retieved:November 13,2020.
    [25] W. Zhou, A. C. Bovik, H. R. Sheikh, and E. P. Simoncelli, "Image quality
    assessment: from error visibility to structural similarity," IEEE Transactions on
    Image Processing, vol. 13, no. 4, pp. 600-612, 04/01/ 2004, doi:
    10.1109/TIP.2003.819861.
    [26] M. P. Sampat, W. Zhou, S. Gupta, A. C. Bovik, and M. K. Markey, "Complex
    Wavelet Structural Similarity: A new image similarity index," IEEE Transactions
    on Image Processing, vol. 18, no. 11, pp. 2385-2401, 11/01/ 2009, doi:
    10.1109/TIP.2009.2025923.
    [27] Wikipedia, "Histogram of oriented gradients," [Online]. Available:
    https://en.wikipedia.org/wiki/Histogram_of_oriented_gradients. , last retieved:
    November 16,2020.
    [28] N. Dalal and B. Triggs, "Histograms of oriented gradients for human detection,"
    vol. 1, ed. Los Alamitos, CA, USA, 2005 IEEE Computer Society Conference on
    Computer Vision and Pattern Recognition (CVPR'05), 20-25 June 2005, DOI:
    10.1109/CVPR.2005.177
    [29] 維基百科, "畢氏定理," [Online]. Available:
    https://zh.wikipedia.org/wiki/%E7%95%A2%E6%B0%8F%E5%AE% ,
    last retieved:November 8,2020.
    [30] Wikipedia, "Support vector machine," [Online]. Available:
    https://en.wikipedia.org/wiki/Support_vector_machine.,last retieved:October 20,2020.
    [31] Wikipedia, "Naive Bayes classifier," [Online]. Available:
    https://en.wikipedia.org/wiki/Naive_Bayes_classifier. , last retieved:November 11,2020.
    [32] Wikipedia, "Logistic regression," [Online]. Available:
    https://en.wikipedia.org/wiki/Logistic_regression. , last retieved:November 5,2020.
    [33] Wikipedia, "Random forest," October. 25, 2020. [Online]. Available:
    https://en.wikipedia.org/wiki/Random_forest. , last retieved:November 5,2020.
    [34] Wikipedia, "Decision tree," [Online]. Available:
    https://en.wikipedia.org/wiki/Decision_tree. , last retieved:October 13,2020.
    [35] Wikipedia, "Binary image," [Online]. Available:
    https://en.wikipedia.org/wiki/Binary_image. , last retieved:June 5,2020.
    [36] Wikipedia, "Gaussian blur," [Online]. Available:
    https://en.wikipedia.org/wiki/Gaussian_blur. , last retieved:October 31,2020.
    [37] Wikipedia, "Otsu's method," [Online]. Available:
    https://en.wikipedia.org/wiki/Otsu%27s_method. , last retieved: October 13,2020.
    [38] 維基百科, "感光度," [Online]. Available:
    https://zh.wikipedia.org/wiki/%E6%84%9F%E5%85%89%E5%BA%A6. ,
    last retieved: October 10,2020.
    [39] Wikipedia, "Gamma correction," [Online]. Available:
    https://en.wikipedia.org/wiki/Gamma_correction. , last retieved: September 28,2020.
    [40] scikit-image, "Histogram of oriented gradients," [Online].
    https://scikit-image.org/docs/dev/auto_examples/features_detection/plot_hog.html. ,
    last retieved: October 20,2020.
    [41] F. a. V. Pedregosa, G. and Gramfort, A. and Michel, V.and Thirion, B. and Grisel,
    O. and Blondel, M. and Prettenhofer, P. and Weiss, R. and Dubourg, V. and
    Vanderplas, J. and Passos, A. and Cournapeau, D. and Brucher, M. and Perrot, M.
    and Duchesnay, E., "Scikit-learn: Machine Learning in Python," Journal of
    Machine Learning Research, 2011. arXiv:1201.0490v4 [cs.LG] , [Online]. Available:
    https://arxiv.org/abs/1201.0490., last retieved:June 5,2018.
    [42] Wikipedia, "Body mass index (BMI)," [Online]. Available:
    https://en.wikipedia.org/wiki/Body_mass_index.,last retieved: November 28,2020.

    無法下載圖示 校內：2023-03-01公開
    校外：不公開
    電子論文尚未授權公開，紙本請查館藏目錄
    QR CODE