結論

本論文是提出一個透過調整影像內容的前置處理法，用以提高現有的多值化 法的多值化效果，多值化的優點是降階後能保留更多的特徵，如水果的壓傷位置、

腦袋腫瘤的大小在二值化都有可能會消失，多值化則有較高的機會描述這些特徵

，但有優點也有缺點，多值化本身有難做的點如相當冗長的計算時間，但是有最 佳化演算法做搭配的話，就能夠達到壓縮計算時間並保持原有品質的效果，多值 化本身也沒有一個絕對評判效果好壞的機制，我們間接透過輪廓偵測來判斷多值 化的效果優劣，會做輪廓偵測通常有後續的目的，如果能提高邊緣偵測的準確度，

也算是提高了多值化的價值。

本論文的影像調整是基於影像的重要輪廓做背景區塊的處理與頻域濾波的 依據，影像常常有複雜的背景掩蓋了物件或光影干擾等問題，藉由擾亂背景資訊 與濾波處理明暗問題讓包裹重要資訊的輪廓能夠在影像中突顯，希望以這樣的方 式讓多值化時能夠真正的顯現重要的資訊來做後續利用，以輪廓偵測來評估，數 據上也反映了我們的期待，濾波也利用頻譜樣板優化縮短原本需要在空間域與頻 率域之間的頻繁轉換的運算時間，希望多值化也能夠使用在更多與時間賽跑的應 用上。

50

參考文獻

[1] Zhang Tailing, Deng Jizhong, "Application of Computer Vision to the Detection of Pear’s Bruising" Transactions of the Chinese Society of Agricultural Engineering 15.1 205-209 (1999)

[2] Juang Puu-An, Wu Ming-Ni, Shiu Jen-Yun, Yan Hong-Yuan, "Brain tumor segmentation based on otsu clustering with multi-thresholding method" National Computer Symposium 12-20~21 (2007)

[3] Li Kai, Chen Li-An, Cao Jichang, "ID card number identification based on gray scale multi-level" Computer Engineering and Applications 51 191-196 (2015)

[4]

Syu Shin-Syong, "A study of white light interference detection system

[5] M.Sezgin and B.Sankur , "Survey over image thresholding techniques and quantitative performance evaluation" Journal of Electronic Imaging 13.1 146-165 (2004)

[6] N.Otsu, "A threshold selection method from gray level histograms"

IEEE Transactions on Systems, Man, and Cybernetics 62-66 (1979) [7] J.N.Kapur, P.K.Sahoo, and A.K.C.Wong, "A new method for

gray-level picture thresholding using the entropy of the histogram"

Computer Vision, Graphics,and Image Processing 29 273-285 (1985) [8] J.Kennedy and R.Eberhart, "Particle Swarm Optimization" Proceedings

of IEEE International Conference on Neural Networks 1942–1948.

(1995)

[9] Yang Xin-She, "Nature-inspired metaheuristic Algorithms Second Edition" ISBN:9781905986286 81-89 (2010)

[10]Chen kai,Chen Fang, Dai min ,Zhang zhi-sheng and Shi jin-fei , "Fast image segmentation with multilevel threshold of two-dimensional entropy based on firefly algorithm" Optics and Precision Engineering 22 (2014)

[11]https://en.wikipedia.org/wiki/Peak_signal-to-noise_ratio

[12]N.Sri Madhava Raja, V.Rajinikanth and K.Latha, "Otsu based optimal multilevel image thresholding using firefly algorithm" Hindawi

51

Publishing Corporation Modelling and Simulation in Engineering Volume (2014)

[13]S.Arora, J.Acharya, A.Verma, Prasanta K.Panigrahi, "Multilevel thresholding for image segmentation through a fast statistical recursive algorithm" Pattern Recognition Letters 29 119-125 (2008) [14]Liu Dong-ju, Yu Jian, "Otsu method and K-means" Ninth International

Conference on Hybrid Intelligent Systems (2009)

[15]http://mirlab.org/jang/books/dcpr/dcKMeans.asp?title=3-3%20K-mean s%20Clustering

[16]Lin Yi-Guei, "Multilevel Image Thresholding and Handwritten Chinese Character Recognition by Support Vector Machines" 國立屏東大學資訊 工程系碩士論文 (2011)

[17]https://en.wikipedia.org/wiki/Sobel_operator [18]http://www.csie.ntu.edu.tw/~cjlin/libsvm/

[19]http://www.cmlab.csie.ntu.edu.tw/~cyy/learning/tutorials/SVM2.pdf [20]Kuan Chung-Chun, "Contour-guided image binarization by frequency

filtering" 國立屏東大學資訊工程系碩士論文 (2013)

[21]P.Arbelaez, M.Maire, C.Fowlkes and J.Malik. "Contour detection and hierarchical image segmentation" IEEE Transactions on Pattern Analysis and Machine Intelligence 33 898-916 (2011).

[22]P.Arbelaez, et al. "From contours to regions: An empirical evaluation" Computer Vision and Pattern Recognition (2009)

[23]M.Maire, et al. "Using contours to detect and localize junctions in natural images." Computer Vision and Pattern Recognition (2008) [24]H.Cormen, E.Leiserson, L.Rivest and C.Stein , "Introduction to

algorithms Third Edition" ISBN:9780262033848 (2009)

[25]J.Canny, "A computational approach to edge detection" IEEE

Transactions on Pattern Analysis and Machine Intelligence 6 679-698 (1986)

[26]J.M.S.Prewitt, "Object enhancement and extraction " In Picture Processing and Psychopictorics (1970)

[27]L.G.Roberts, "Machine perception of three-dimensional solids" In Optical and Electro-Optical Information Processing (1965)

52

[28]http://www.eecs.berkeley.edu/Research/Projects/CS/vision/grouping /segbench/

[29]L.Najman and M.Schmitt, "Geodesic saliency of watershed contours and hierarchical segmentation" IEEE Transactions on Pattern Analysis and Machine Intelligence 18 1163-1173 (1996)

[30]L.Shapiro, G.Stockman, "Computer Vision" ISBN:9780130307965 69-73 (2002)