跳到主要內容

臺灣博碩士論文加值系統

(18.97.9.169) 您好!臺灣時間:2025/02/09 22:31
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

我願授權國圖
: 
twitterline
研究生:林建弘
研究生(外文):Chien-Hung Lin
論文名稱:使用類神經網路的錠劑藥物影像檢索
論文名稱(外文):Pill Image Retrieval using Neural Networks
指導教授:江蔚文江蔚文引用關係
學位類別:碩士
校院名稱:國立台北護理學院
系所名稱:資訊管理研究所
學門:電算機學門
學類:電算機一般學類
論文種類:學術論文
論文出版年:2006
畢業學年度:94
語文別:中文
論文頁數:88
中文關鍵詞:藥物影像影像特徵影像辨識類神經網路
外文關鍵詞:CBIRpill imageimage featuresimage recognitionneural networks
相關次數:
  • 被引用被引用:2
  • 點閱點閱:349
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:1
隨著民眾教育水準的提升以及一些重大醫療用藥疏失的發生,使民眾對於藥物資訊與用藥安全的需求與日劇增。但不論是使用網際網路或是藉由書籍來尋找藥物資訊,通常只能透過藥名或其他描述藥物功能的關鍵字去查詢。
  影像資料往往很難用文字去描述,當使用者擁有藥錠但遺失藥名的時候,以電腦視覺辨識藥物去查詢藥物資訊,不失為一個好的方法。有鑑於此,本研究提出一個以內容為基礎的影像檢索方法(Content-Based Image Retrieval,CBIR),透過錠劑藥物數位影像中形狀(shape)、大小(scale)、顏色(color)等特徵之擷取,結合類神經網路的分類功能,建立一個錠劑藥物外觀影像檢索模型,以服務醫療人員或一般民眾。
運用數位相機或攝影機取得的藥物影像,先經由自動化的方式擷取影像內容特徵,再進行辨識。本論文提出非文字的查詢方式,以藥物外觀影像找尋影像資料庫中的藥物,來輔助醫療人員及一般民眾。本研究證明了使用類神經網路作為藥物外觀影像系統中辨識工具的可行性。
With the elevation of peoples’ educational level and the occurrence of some serious medication mistakes, the need for correct pharmaceutical information and adequate knowledge of medication safety grows higher and higher. People often look for medicine information on the Internet or in books. However, they can only query using drug names or key words of medicine functions.
Images are often difficult to be described with text. From time to time, users who do not know the name of a medicine need to obtain the information of that medicine. In that circumstance, it’s a good method to enquire medicine information by recognizing medicines using computer vision. A content-based image retrieval method was proposed in this thesis. Shape, scale, and color features of pill images were extracted first and then fed into neural networks for classification. The pill image retrieval model was built by deploying appropriate features and neural networks to serve users.
After obtaining pill images via digital camera, features that represented the images were extracted automatically. The features were then processed for recognition. This thesis proposed a non-character-based method for medicine image retrieval to assist medical staffs and general users. It proved that a pill image recognition system using neural networks is feasible.
致謝 i
摘要 ii
目錄 iv
圖目次 vi
表目次 viii
第一章 緒論 1
1.1 研究背景與動機 1
1.2 研究目的 2
第二章 文獻探討 3
2.1 用藥安全 3
2.3 以內容為基礎的影像檢索系統回顧 12
2.3.1 QBIC 13
2.3.2 VisualSEEk 13
2.3.3 Blobworld 14
2.4 以內容為基礎的藥物影像檢索系統 16
2.4.1 RDIIS 16
2.5 影像特徵 18
2.5.1 顏色特徵 18
2.5.1.1 色彩直方圖(color histogram) 18
2.5.1.2 色彩集合(color set) 19
2.5.1.3 色彩矩(color moments) 19
2.5.2 形狀特徵 20
2.5.2.1 鏈碼(chain code) 20
2.5.2.2 傅利葉描述子(Fourier descriptor) 21
2.5.2.3 不變矩(invariant moments) 21
2.5.2.4 Zernike矩(Zernike moments) 22
2.5.3 紋理特徵 23
2.5.3.1 注水法(water-filling) 23
2.5.3.2 小波矩(wavelet moments) 24
2.5.4 類神經網路分類器 24
2.5.4.1 類神經網路 24
2.5.4.2 類神經網路模型的建構 26
第三章 研究方法 27
3.1 低階程序:藥物影像資料蒐集及前置處理 28
3.1.1 藥物影像蒐集 28
3.1.2 前置處理 29
3.1.2.1 影像大小縮放 29
3.1.2.2 去除雜訊 30
3.2 中階程序:藥物影像特徵萃取 31
3.2.1 影像分割 31
3.2.2 藥物影像特徵萃取 31
3.2.2.1 形狀與大小特徵 31
3.2.2.2 顏色特徵 32
3.3 高階程序:藥物影像特徵辨識模型之開發 32
3.3.1 結合類神經網路及Zernike矩於影像形狀、大小之辨識 32
3.3.1.1 實驗設計 33
3.3.1.2 實驗結果 35
3.3.1 結合類神經網路及不變矩於藥物影像形狀之辨識 40
3.3.2.1 實驗設計 40
3.3.2.2 實驗結果 41
3.4 結果比較 44
第四章 實證分析 46
4.1 檢索介面 46
4.2 檢索演算法 47
4.3 檢索正確率分析 47
第五章 結論與建議 49
5.1 研究結論 49
5.1 研究建議 49
參考文獻 50
附錄 53
A 自行拍攝之錠劑藥物影像 53
[1]C. Carson, S. Belongie, H. Greenspan, and J. Malik, “Region-based image querying”, Proc. IEEE CAIVL, 1997.
[2]C. C. Chang and Y. K. Chan, “A Fast Filter for image retrieval Based on Color-Spatial Feature”, Ph.D. Dissertation, National Chung Cheng University, 1989.
[3]Z. Geradts, H. Hardy, A. Poortman, and J. Bijhold. “Evaluation of content-based image retrieval methods for a database of logos on drug tablets”, Proc. SPIE Vol. 4232, p. 553-562, 2001.
[4]P. Y. Hsu, “Trademark Image Retrieval using Shape Feature”, Master Thesis, National Dong Hwa University, 2000.
[5]M. K. Hu, “Visual pattern recognition by moment invariants”, IRE Trans. on Inform. Theory, Vol. IT-8, pp. 179-187, 1962.
[6]A. K. Jain and A. Vailaya, “Image retrieval using color and shape”, Pattern Recognit., vol. 29, pp. 1233–1244, 1996.
[7]W. Y. Kim and Y. S. Kim, “A region-based shape descriptor using Zernike moments”, Signal Processing: Image Communication, Vol. 16, pp. 95-102, 2000.
[8]S. H. Lai, ” Color Retrieval of Butterfly Images,” Master Thesis, Dept. CSIE, Univ. of NTU, p4, 2002.
[9]A. Laine and J. Fan, “Texture classification by wavelet packet signatures”, IEEE Tran. Pattern Anal. Machine Intell., Vol. 15, No. 11, pp. 1186-1191, 1993.
[10]B.M. Mehtre, M. S. Kankanhalli, and W. F. Lee, “ Content-based image retrieval using a composite color-shape approach”, Information Processing & Management, vol. 34, no.1, pp. 109-120, 1998.
[11]W. Niblack, R. Barber, W. Equitz, M. Flickner, E. Glasman, D. Petkovic, P.Yanker, and C. Faloutsos, “The QBIC project: querying images by content using color, texture, and shape,” Research Report, No.9203, pp.23~32, IBM Almaden Research Center, 1993.


[12]J. R. Smith and S. F. Chang, “Single Color Extraction and Image Query,” International Conference on Image Processing (ICIP-95), Washington, DC, Oct. 1995
[13]J. R. Smith and S. F. Chang, “VisualSEEk: A fully automated content-based image query system”, in ACM Multimedia Conference, Boston, MA, USA, 1996.
[14]J. R. Smith and S. F. Chang, “Visually searching the web for content”, IEEE Trans. Multimedia, Vol. 4, No. 3, pp. 12-20, 1997.
[15]M. Stricker and M. Orengo, “Similarity of Color Images”, in Proc. SPIE Storage and Retrieval for Still Image and Video Databases III, pp. 381-392, San Jose, CA, USA, February 1995.
[16]K.S. Tang, C.Y. Chan, K.F. Man, and S. Kwong, “Genetic Structure for NN topology and Weights Optimization, Genetic Algorithms in Engineering Systems: Innovations and Applications,” First International Conference on GALESIA, pp. 250-255, 1995.
[17]J. K. Wu, C. P. Lam, B. M. Mehtre, Y. J. Gao, and A. D. NarasiMhalu, “Content-based retrieval for trademark registration,” Multimedia Tools and Applications, Vol. 3, pp. 245-267, 1996.
[18]S. Zhang and K. K. Ma, “A novel shape matching method using biological sequence Dynamic alignment,” in Proceedings of IEEE International Conference on Multimedia and Expo, 2000.
[19]X. S. Zhou and T. S. Huang, “ Image retrieval: feature Primitives, feature representation, and relevance feedback,” in Proc. IEEE Workshop on Content-Based Access of Image and Video Libraries, in Conjunction with CVPR'00, pp. 10-14, 2000.
[20]GNU Image Finding Tool, http://www.gnu.org/software/gift/
[21]WebSEEk, the World Wide Web oriented text/image search engine, Demo:http://www.ee.columbia.edu/~sfchang/demos.html/.
[22]Health 4 Ever,常用藥品查詢系統,http://www.health4ever.com/drug/index.htm
[23]行政院衛生署、臺北醫學大學藥學系,2004藥物實體外觀辨識手冊(含藥物辨識查詢與用藥安全光碟光碟) ,2004

[24]林建弘,結合類神經網路及Zernike Moments於錠劑藥物形狀、大小之辨識,工程科技與中西醫學應用研討會,2006,pp. 540-545
[25]吳靜宜,影像內容檢索系統之使用研究,輔仁大學圖書資訊研究所碩士論文,2003
[26]財團法人醫院評鑑暨醫療品質策進會,“JCAHO 2005年病人安全目標翻譯內容(93.12.20修訂版)",財團法人醫院評鑑暨醫療品質策進會,台灣,2005
[27]謝家興,運用以內容為基礎之影像擷取於藥物辨識之研究,臺北醫學大學醫學資訊研究所碩士論文,2005
[28]台灣魚類資料庫,http://fishdb.sinica.edu.tw/
[29]長庚紀念醫院,用藥指導單張查詢系統,http://www.cgmh.org.tw/asproot/medic/medic.asp
[30]衛生署用藥需求調查
http://www.ettoday.com/2004/01/14/23-1572697.htm
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top