因應農業人力之不足，以機械自動化採收蔬果為近年來之趨勢，而草莓之自動採收
最關鍵處為判斷其果實使否成熟並找出成熟果實之果柄採摘位置。本研究目的旨在結合
機器視覺之系統開發，能辨識出草莓成熟度並找出適合機械採摘之果柄位置。
本研究選用草莓品種為佐賀清香進行實驗，以傳統邏輯推論方法及自適應類神經模
糊推論方法辨識草莓成熟度。首先將草莓圖片與農民討論，並建立草莓成熟度分類資料
庫，透過影像中HSL色層分析，計算出草莓表皮淡紅色、中紅、深紅及綠色面積比例，
以傳統邏輯推論方法撰寫程式，推算出其成熟度並與農民採收經驗進行比對驗證。自適
應類神經模糊推論方法則以草莓表皮顏色面積比例為輸入，成熟度為輸出，首先模擬農
民專家建構出IF-THEN規則，並利用類神經之學習能力調整系統參數，以提高其準確性。
成熟草莓果柄採摘位置之辨識則以預先建立之草莓果柄樣本，以色彩模式匹配方法在果
實上方之合理工作區域內尋找辨識果柄位置，並透過雙眼立體視覺公式計算其深度。
本研究實驗結果，傳統邏輯與農民辨識草莓成熟度其辨識準確率為76%，以自適應
類神經模糊推論方法辨識草莓成熟度其辨識準確率可提高至93%。透過草莓果柄樣本背
景佔30%之樣本，辨識果柄位置成凾率達94%。本研究開發雙眼立體視覺可計算出拍攝
物與攝影機之深度距離，提供採收機器人剪取草莓果柄之深度，未來與機械手臂整合後
將可達成草莓自動化採收之作業。

Harvesting strawberries by robots will be the future trend to solve the problem caused by
the shortage of the agricultural manpower. One of the critical factors for automatic harvesting
is to find strawberries with sufficient maturity and their locations. The object of this research
is to develop a machine vision system to identify the maturity of strawberries and locate their
suitable stem positions for mechanical harvesting.
This study used Saga-Honoka type strawberries for experiment. The images of
strawberries were collected and the degrees of the maturities of strawberries were first
classified by experienced farmers to build the database for further maturity classification. The
degrees of the red colors on the fruit surface were categorized into three varieties of red colors,
light red, middle, red and deep red. The area ratios of three red colors were counted using
HSL color model. The traditional logic inference method was first used to estimate the
maturities based on the area ratios of the red colors. The Adaptive Neuro-Fuzzy Inference
System (ANFIS) method was then used to classify the maturities of the strawberry. First,
ANFIS emulated the farmers to derive several ―IF-THEN‖ fuzzy rules. The learning method
of the artificial neural network was then applied to adjust ANFIS parameters in order to
improve their accuracy. The color pattern matching method was used to locate the stems for
harvesting. The searching area for color pattern matching was constricted within the area
above the fruits to shorten the time. The depth of the stem position was calculated by the
binocular stereo vision formula.
The result showed that the successful rate for maturity classification using traditional
logic method was only 76%. The successful rate for maturity classification using ANFIS
method can be increased to 93%. The result for comparing templates with different
background ratios for color pattern matching showed that the template with about 30%
background can locate the stems pattern with 94% successful rate. The binocular stereo vision
can also successfully predict the depth of the distance between the stem and the camera. The
developed system could be used to integrate with the robot arm to harvest the strawberries in
the future.

致謝 ............................................................................................................ ii
摘要 ..................................................................................................... iii
ABSTRACT ..........................................................................................................iv
目錄 .................................................................................................. v
圖目錄 ............................................................................................................. viii
表目錄 ................................................................................................................ xi
第一章 緒論 ...................................................................................................... 1
1.1 前言 .............................................................................................................. 1
1.2 研究目的 .......................................................................................................... 2
第二章 文獻探討 .................................................................................................... 3
2.1 草莓背景介紹 ............................................................................................ 3
2.2 水果成熟度檢測技術 ................................................................................................. 4
2.3 影像技術於水果之應用 ............................................................................................. 6
2.3.1 自動採收系統 ...................................................................................................... 6
2.3.2 機器視覺於水果自動分級之應用 ....................................................................... 9
2.4 影像處理技術 ............................................................................................ 10
2.4.1 色彩模型 ............................................................................................... 10
2.4.2 二值化 .................................................................................................. 11
2.4.3 形態學 ................................................................................................... 11
2.4.4 色彩模式匹配 .................................................................................................... 13
2.4.5 雙眼立體視覺 .................................................................................................... 16
2.5 人工智慧法.................................................................................................. 18
2.5.1 模糊理論 ................................................................................................... 19
2.5.2 類神經網路 ............................................................................................... 19
2.5.3 自適應類神經模糊之理論 ................................................................................. 21
2.5.4 自適應類神經模糊系統在農業之應用 ............................................................. 24
第三章 材料與方法 ............................................................................................... 25
3.1 系統架構 ....................................................................................................... 25
3.2 影像擷取系統 ................................................................................................. 26
3.2.1 取像帄台設計 .................................................................................................... 26
3.2.2 彩色攝影機 .................................................................................................... 27
3.2.3 照明設備 ..................................................................................................... 30
3.2.4 建立草莓圖片資料庫 ........................................................................................ 31
3.3 影像處理系統 .................................................................................................. 32
3.3.1 軟體 ......................................................................................................... 32
3.3.2 草莓果實參數分析系統..................................................................................... 33
3.3.3 草莓之成熟度辨識 ............................................................................................ 39
3.3.3.1 農民採收經驗成熟度辨識 .......................................................................... 39
3.3.3.2 傳統邏輯成熟度辨識 .................................................................................. 40
3.3.3.3 自適應類神經模理論於辨識草莓成熟度 ................................................... 43
3.3.4 MATLAB 與LabVIEW整合應用於辨識草莓成熟度 ....................................... 49
3.3.5 草莓果柄位置辨識 ............................................................................................ 50
3.3.6 雙眼視覺之空間座標定位 ................................................................................. 54
第四章 詴驗方法 ..................................................................................................... 56
4.1 草莓生長位置與影像計算位置之深度詴驗............................................................. 56
4.2 草莓成熟度辨識詴驗 ............................................................................................... 58
4.2.1 以傳統邏輯辨識草莓果實成熟度之詴驗 .......................................................... 58
4.2.2 以自適應類神經模糊系統(ANFIS)辨識草莓果實成熟度詴驗 ......................... 58
4.3 草莓果柄樣本之背景比例對辨識成凾率之影響詴驗 ............................................. 59
4.4 草莓成熟度與果柄位置辨識系統之整合詴驗 ......................................................... 60
第五章 結果與討論 ................................................................................................ 61
5.1 草莓成熟度與果柄位置辨識系統介面與凾能 ......................................................... 61
5.2 草莓生長位置與影像計算位置之深度詴驗結果 ..................................................... 64
5.3 草莓成熟度辨識結果 ............................................................................................... 65
5.3.1 以傳統邏輯辨識草莓果實成熟度詴驗結果 ...................................................... 65
5.3.2 以自適應類神經模糊系統(ANFIS)辨識草莓果實成熟度詴驗結果 ................. 67
5.4 草莓果柄樣本之背景比例對辨識成凾率之影響詴驗結果 ..................................... 69
5.5 草莓成熟度與果柄位置辨識系統之詴驗結果 ......................................................... 71
第六章 結論 ...................................................................................................... 74
第七章 建議及未來展望 ....................................................................................... 75
第八章 參考文獻 .................................................................................................. 76
第九章 附錄 .......................................................................................................... 81

1. 王自存。2010。水果採後處理技術及未來趨勢。2010 年宜蘭地區果樹產業發展研
討會專凼，87-98。
2. 行政院農業委員會。2007。草莓主題館。台北: 行政院農業委員會。網址：http://km
web.coa.gov.tw/subject/ct.asp?xItem=84600&ctNode=2050&mp=126&kpi=0。上網日
期：2014-08-20。
3. 行政院農業委員會農糧署。2013。102年蔬菜生產概況。農情報告資源網址： http://
www.afa.gov.tw/GrainStatistics_index.asp?CatID=142。上網日期：2014-07-08。
4. 李宗霖、蔡清標、謝榮哲、徐月娟、陳進益、劉聖義。2002。倒傳遞類神經網路在
潮汐補遺之應用。台灣海洋工程學會。
5. 李柔靜。2009。番茄採收機器視覺系統之研究。碩士論文。台北：國立台灣大學生
物產業機電工程學系。
6. 邱俊智。2010。自適應性類神經模糊推論系統於客製化生產環境之預測應用。2010
年資訊科技國際研討會論文集。
7. 林銘君。1999。以ANFIS為架構設計大氣中可降水、液態水的資料反衍系統。碩士
論文。雲林：雲林科技大學電機工程技術研究所。
8. 林東賦。2001。應用影像處理技術與類神經網路理論於非織物瑕疵辨識。碩士論文。
台北：國立台灣科技大學纖維及高分子工程技術研究所。
9. 林育正。2009。以關聯式動態規劃法做雙眼立體視覺偵測。碩士論文。桃園：國立
中央大學資訊工程研究所。
10. 林家鋒、邱奕志、陳世銘。2009。應用LabVIEW於無人化水果採收系統之設計。ET
電子技術。277: 92-96。
11. 財團法人車輛研究測詴中心。2011。立體視覺技術於車輛領域之應用。彰化:財團
法人車輛研究測詴中心。網址：http://www.artc.org.tw/chinese/03_service/03_02detail.
aspx?pid=1896。上網日期：2014-07-20。
12. 陳秉鴻。2009。機器視覺應用於百香果田間撿拾機器之研製。碩士論文。宜蘭：國
立宜蘭大學生物機電工程研究所。
13. 陳奕安、歐陽鋒、邱奕志。2013。以影像處理技術辨識草莓果實成熟度及果柄採摘
位置。2013生機與農機學術研討會，199-204。
14. 張懷祖。1994。類神經網路技術介紹。電腦與通訊。28: 16-30。
15. 葉怡成。1995。類神經網路-方法應用與實作。台北：儒林圖書。
16. 御欽工業有限公司。2014。CQ-LV8003A規格。彰化：http://www.cheerwell-lighting
.com.tw/main.php?fid=04。上網日期：2013-11-20。
17. 楊本源。2011。設施內番茄採收機器人爪具之研製。碩士論文。宜蘭：國立宜蘭大
學生物機電工程研究所。
18. 廖育盛。2008。以對應點為基礎應用立體視覺之自動停車系統。碩士論文。台北：
國立台北科技大學車輛工程研究院。
19. 維基百科。2013。RGB色彩編碼。台北：維基百科。網址：http://zh.wikipedia.org/zh-tw/
%E4%B8%89%E5%8E%9F%E8%89%B2%E5%85%89%E6%A8%A1%E5%BC%8F。
上網日期：2014-8-20。
20. 蘇木春、張孝德。2007。機器學習：類神經網路、模糊系統以及基因演算法則。三
版。台北：全華。
21. Abdullah, M. Z., L. C. Guan, K. C. Lim, and A. A. Karim. 2004. The applications of
computer vision system and tomographic radar imaging for assessing physical properties
of food. Journal of Food Engineering 61: 125–135.
22. Blasco, J., N. Aleixos, E. Molt. 2003. Machine vision system for automatic quality
grading of fruit. Biosystems Engineering 85(4): 415–423.
23. Bulanon, D. M., T. Kataoka, H. Okamoto and S. Hata. 2004. Determining the 3-D
location of the apple fruit during harvest. ASAE Publication No. 701P1004. Kyoto,
Japan.
24. Cubero, S., M. P. Diago, J. Blasco, J. Tardaguila, B. Millan. and N. Aleixos. 2014. A
new method for pedicel/peduncle detection and size assessment of grapevine berries and
other fruits by image analysis. Biosystems engineering 117: 62-72.
25. Gamal, E., N. Atef, W. Ning, V. Clément. 2008. Spectral methods for measuring quality
changes of fresh fruits and vegetables. Stewart Postharvest Review 4(4): 1-13.
26. Gatica, G., B. Stanley, J. Ceroni. and L. Gastón. 2013. Olive fruits recognition using
neural networks. Procedia Computer Science 17: 412-419.
27. Gonzalez, R. C., and Woods, R. E. 1992. Digital imaging processing. Massachusetts:
Addison-Wesley.
28. Guo, F., Q. Cao, and M. Nagata. 2008. Fruit detachment and classification method for
strawberry harvesting robot. International Journal of Advanced Robotic Systems 5(1):
41-48.
29. Hayashi, S., S. Kenta, Y. Satoshi, K. Ken, K. Yasushi, K. Junzo, K. Mitsutaka. 2010.
Evaluation of a strawberry-harvesting robot in a field test. Biosystems Engineering
105(2): 160-171.
30. Hayashi, S., S. Yamamoto, S. Saito, Y. Ochiai, Y. Kohno, K. Yamamoto. and M. Kurita.
2012. Development of a movable strawberry-harvesting robot using a travelling platform.
5th Automation Technology for Off-Road equipment Conference.
31. Imagingsorce. 2014. Color camera specifications. Taiwan: Taipei. Available at:
http://www.theimagingsource.com/zh_TW/products/cameras/gige-cmos-ccd-color/dfk23
gm021/. Accessed 15 November 2013.
32. Jang, J. S. 1993. ANFIS: Adaptive-Network-based fuzzy inference systems, Man and
Cybernetics. IEEE Transactions on Systems 23(3): 665-685.
33. Janisiewicz, W. J., W. S. Conway. 2010. Combining biological control with physical and
chemical treatments to control fruit decay after harvest. Stewart Postharvest Review 6(1):
1-16.
34. Jayas, D. S., C. Karunakaran. 2005. Machine vision system in postharvest
technology. Stewart Postharvest Review 1(2): 1-9.
35. Kader, A. A. 2002. Postharvest technology of horticultural crops. 3rd ed. Univ. of
California, Agriculture & Natural Resources, Publication.
36. Kim, S. C., G. S. Han, S. C. Jung, T. H. Le. and H. Hwang. 2008. Development of
robotic harvest system for bench-type strawberry cultivation. In "Proceedings of the 4th
International Symposium on Machinery and Mechatronics for Agriculture and
Biosystems Engineering". Taichung, Taiwan.4: BR21-28.
37. McCulloch, W. S., W. Pitts. 1943. A logical calculus of the ideas immanent in nervous
activity. The bulletin of mathematical biophysics 5(4): 115-133.
38. Nagata, M., Y. Cui. and G. Jasper. 2006. Study on cartesian-type harvesting robot for
strawberry. In "JBio-Robotics m Preprints of 3rd IFAC International workshop on
Bio-Robotics, Information Technology and Intelligent Control for Bioproduction
Systems". Sapporo, Japan: IFAC: 266-270.
39. Naoshi, K., N. Kazunori, H. Shigehiko, O. Tomohiko. and K. Kotaro. 2005. A new
challenge of robot for harvesting strawberry grown on table top culture. In 2005 ASABE
Annual International Meeting. Tampa, Florida.
40. National Instruments. 2011. Color pattern matching. Taiwan: Taipei. Available at: http://
zone.ni.com/reference/en-XX/help/372916L-01/nivisionconcepts/color_pattern_matchin
g/. Accessed 22 July 2014.
41. Ou-Yang, F., C. Yi-An, C. Yi-Chich, T. Jui-Pin. 2014. Application of Adaptive
Neuro-Fuzzy Inference System (ANFIS) to develop a machine vision system for
strawberry maturity classification. In "Proceedings of the 7th International Symposium
on Machinery and Mechatronics for Agriculture and Biosystems Engineering", 775-780.
42. Pedreschi, F., J. Leon, D. Mery. and P. Moyano. 2006. Development of a computer vision
system to measure the color of potato chips. Food Research International 39(10):
1092-1098.
43. Rajendra, P., K. Naoshi, N. Kazunori, K. Junzo, K. Mitsutaka, S. Tomowo, H. Shigehiko,
Y. Hirotaka. and K. Yasushi. 2009. Machine Vision Algorithm for Robots to Harvest
Strawberries in Tabletop Culture Greenhouses. EAEF 2(1): 24-30.
44. Seiichi, A., K. Naoshi, M. Mitsuji. 2004. Strawberry harvesting robot on table-top
culture. ASAE Paper No.043089. Ottawa, Ontario, Canada.
45. Shigehiko, H., O. Tomohiko, K. Kotaro, G. Katsunobu, and K. Naoshi. 2005. Robotic
harvesting technology for fruit vegetables in protected horticultural production. In
"Information and Technology for Sustainable Fruit and Vegetable Production", 227-236.
Montpellier , France.
46. Thompson, A. K. 2003. Fruit and vegetables: harvesting, handling, and storage.
Blackwell Publishing Ltd. Oxford, UK. Bulletin of Mathematical Biophysics 5: 115-133.
47. Tomowo, S., K. Naoshi, K. Mitsutaka, N. Kazunori, R. Peter, K. Junzo, H. Shigehiko, K.
Ken and S. Kenta. 2008. Strawberry harvesting robot for fruits grown on table top
culture. ASABE Paper No. 084046.
48. Woods, G. 2009. Digital Image Processing. 3rd ed. 620-651. Taiwan: Prentice Hall.
49. Xu, L., Y. Zhao. 2010. Automated strawberry grading system based on image
processing. Computers and Electronics in Agriculture 71: 32-39.
50. Zadeh, L. A. 1965. Fuzzy sets. Information and Control 8: 338-353.
51. Zheng, H., B. Jiang, H. Lu. 2011. An adaptive neural-fuzzy inference system (ANFIS)
for detection of bruises on Chinese bayberry (Myrica rubra) based on fractal dimension
and RGB intensity color. Journal of Food Engineering 104: 663-667.