本研究完成一套稻米品種潔淨度自動化辨識系統，其功能包括自動進出料、計數、擷取影像、特徵萃取、品種辨識及建置影像資料庫，並應用此系統針對紅米與六種不同種的稻米進行品種辨識，平均系統效能為113顆/分、平均辨識率為96%。
本研究利用影像處理技術針對稻米種子萃取其形態與色彩特徵，作為貝氏分類器、倒傳遞類神經網路及支持向量機的輸入向量，針對103、104及105年度的台梗9號、台南11號與台梗14號之原原種稻米種子進行訓練與測試，其平均辨識率分別為98.61%、94.33%及93.94%。由結果顯示，本研究開發之稻米品種潔淨度自動化辨識系統可有效地辨識稻米種子品種。

This paper presents a novel machine vision-based auto-recognizing system for paddy seed purification. The system comprises an inlet-outlet mechanism, machine vision hardware and software, and control system for recognizing seed varieties. Five varieties and red paddy seeds can be recognized using the system. The average speed of recognition is as high as 113 seeds/min. The results show the accuracies of classification to be 96.0%.
The proposed method can estimate the shape and color features of seeds that are provided as input vector of Bayesian, back-propagation neural network, and support vector machine classifiers in order to classify Taichung Sen 10, Taikong 9, Tainan 11, Taikong 14, and Taichung 192 paddy seeds. The results show the accuracies of recognition to be 98.2%, 90.2%, 92.3%, 90.0%, 91.3% as “yes” and “no”, respectively. The average accuracies are 98.61%, 94.33%, 93.94% to recognize paddy seeds for 2014, 2015, and 2016 years. The experimental results indicate that paddy seeds can be recognized efficiently using the developed system.

目錄
摘要 i
Abstract ii
目錄 iii
圖目錄 v
表目錄 viii
第一章 緒論 1
1.1 前言 1
1.2 研究動機 1
1.3 研究目標 2
1.4 論文架構 2
第二章 文獻探討 3
2.1 稻米種子介紹 3
2.2 文獻回顧 8
第三章 理論分析 11
3.1 色彩模型 11
3.2 Otsu演算法 13
3.3 Freeman鏈碼邊界描述 14
3.4 凸包演算法 15
3.5 橢圓傅立葉描述子 16
3.6 倒傳遞類神經網路 18
3.7 貝氏分類器 21
3.8 支持向量機 23
第四章 紅米種子辨識系統之初探 28
4.1 稻米種子透光度光源試驗 29
4.2 紅米辨識系統 31
4.3 探討紅米辨識系統之實驗結果 34
第五章 稻米品種潔淨度自動化辨識系統之架構 36
5.1 實驗樣本 36
5.2 實驗設備 38
5.3 稻米種子特徵萃取 45
5.4 稻米種子品種辨識 51
5.5 稻米種子品種辨識軟體 53
5.6 稻米品種潔淨度自動化辨識系統之介紹 55
第六章 結果與討論 57
6.1 稻米種子自動化進出料裝置 57
6.2 稻米品種潔淨度自動化辨識系統 61
6.3 年度分類器 65
第七章 結論與未來展望 76
7.1 結論 76
7.2 未來展望 77
參考文獻 78
附錄A 稻米品種潔淨度自動化辨識系統之硬體規格 81

[1]呂奇峰。水稻三級繁殖制度及採種技術。台南區農業專訊。2015。94:1-4。
[2]黃卯昌、許鐈云、張仁銓、周永吉、黃亮白、蘇士閔、陳易徵、洪建民、黃玉梅。種種守護-臺灣水稻種子檢查介紹。種苗科技專訊。2013。84:18-21。
[3]侯福分。優良水稻栽培管理技術手冊。2009。行政院農業委員會農糧署。
[4]戴振洋、張致盛。臺中區農業改良場歷年育成品種專輯。2009。行政院農業委員會台中區農業改良場。
[5]陳素娥、林孟輝。有機水稻專輯。桃園區農業專訊。2003。62:12-18。
[6]種苗改良繁殖場種子檢查室。102年米檢人員講習。2013。
[7]International Seed Testing Association (ISTA). International Rules for Seed Testing. Vol. 2015.
[8]Chaugule A.A., S.N. Mali. Identification of paddy varieties based on novel seed angle features. Computers and Electronics in Agriculture 2016, 123: 415-422.
[9]Huang K.Y., M.C. Chien. A Novel Method of Identifying Paddy Seed Varieties. Sensors 2017, 17(4):809.
[10]簡貿謙。應用機器視覺於台灣五大水稻種子品種辨識之研究。碩士論文。2015。台中：國立中興大學生物產業機電工程研究所。
[11]溫惠雯。糙米品質檢測系統之研製。碩士論文。1996。台中：國立中興大學生物產業機電工程研究所。
[12]凃亞廷。咖啡公豆母豆自動選別裝置之開發。碩士論文。2015。台中：國立中興大學生物產業機電工程研究所。
[13]Huang K.Y., J.F. Cheng. A Novel Auto-Sorting System for Chinese Cabbage Seeds. Sensors 2017, 17(4):886. 
[14]Golpour I., J.A. Parian, R.A. Chayjan. Identification and Classification of Bulk Paddy, Brown, and White Rice Cultivars with Colour Features Extraction using Image Analysis and Neural Network. Journal of Food Science 2014, 32(3):280-287.
[15]Pazoki A.R., F. Farokhi, Z. Pazoki. Classification of rice grain varieties using two artificial neural networks(MLP and Neuro-Fuzzy). Journal of Animal & Plant Sciences 2014, 24(1):336-343.
[16]Kaur H., B. Singh. Classification and Grading Rice Using Multi-Class SVM. International Journal of Scientific and Research Publications 2013, 3:1-5.
[17]Gonzalez R.C., R.E. Woods. Digital Image Processing 3rd Edition. Pearson Education Ltd.
[18]Otsu N. A Threshold Selection Method from Gray-Level Histograms. IEEE Transactions on Systems, Man, and Cybernetics 1979, 9:62–66.
[19]Freeman H. On the Encoding of Arbitrary Geometric Configurations. IRE Transactions on Electronic Computers 1961, EC-10:260—268.
[20]Jarvis R.A. On the identification of the convex hull of a finite set of points in the plane. Information Processing Letters 1973, 2:18-21.
[21]Kuhl F.P., C.R. Giardina. Elliptic Fourier Feature of a Closed Contour. Computer Graphic and Image Processing 1982, 18: 236-258.
[22]Rumelhart D.E.; G.E. Hinton, R.J. Williams. Learning representations by back-propagating errors. Nature 1986, 8: 533–536.
[23]Duda R.O., P.E. Hart. D.G. Stork. Pattern Classification. John Wiley & Sons, 2nd Edition.
[24]Cortes C., V. Vapnik. Support-Vector Networks. Machine Learning 1995, 20(3):273-297.
[25]Ben-Hur A., D. Horn, H.T. Siegelmann, V. Vapnik. Support Vector Clustering. Journal of Machine Learning Research 2001, 2: 125-137.
[26]Hsu C.W., Lin C.J. A comparison of methods for multi-class support vector machines. IEEE Transaction on Neural Networks 2002, 13(2): 415-425.
[27]Young Y.T., T.W. Calvert. Classification Estimation and Pattern Recognition. Elsevier Science & Technology 1974, 1st Edition.
[28]Chang C.C., C.J. Lin. LIBSVM : a library for support vector machines. ACM Transactions on Intelligent Systems and Technology 2011, 2:1-27.