臺灣博碩士論文加值系統

在亞洲，每一年飛蝨(Rice Planthopper, RPH)對稻田都有著相當嚴重的侵害，尤其是在東南亞地區，台灣的稻田也是幾乎每年都遭受飛蝨的侵害所苦。飛蝨極小且易散播，所以能有效掌握飛蝨的出沒，才能最快的預防飛蝨的擴大，輔助農民觀測飛蝨的出沒情況，在對的時機點噴灑農藥才是最有幫助的方式。在複雜的稻田影像中，影像處理能夠有效的幫助發現飛蝨，首先在高畫素的影像中進行裁切，我們只關注位在中央感興趣的稻株，切割掉左右兩邊的影像，其次在中央感興趣的植株上尋找飛蝨，在此對影像中的物件做色彩的分析，將色彩資訊的相對關係作為分類依據，排除非飛蝨的pixel，最後得到含有飛蝨及其疑似物的二值化影像，並對二值化影像進行標記，標記出飛蝨便於觀測。這是一套能快速取得感興趣區域的方法，留下完整的飛蝨影像，並且能夠降低後續欲對飛蝨進行應用處理的負擔，減少處理的時間。

Rice Planthopper (RPH) infestation in paddy field is a serious disaster in Asia almost every year, particularly Southeast Asia. It is still suffered RPHs in Taiwan. RPHs are very small and spread easily. Since control RPHs growth is effective to prevent RPH infestation, it is important for farmer to sprinkle pesticides at right time before RPH growth. Preprocess image that complex field scene is helpful to find RPH. First, get rectangle region of interest (ROI) in HD image. We focus on the rice stem in the middle of image and remove the both side in the image. Then, get RPHs in the ROI. Get color information on objects in the ROI and do color analysis. Finally, use decision tree algorithm by relative of color information to get binary image that contain RPHs and something like that and remove pixels without RPHs and label RPHs to observe easily in the binary. This paper propose a method that get ROI quickly. It is useful to reduce executing time and loading for follow-up action and obtain clearly RPH ROI image.

摘要 I
ABSTRACT II
TABLE OF CONTENTS III
LIST OF FIGURES IV
LIST OF TABLES V
CHAPTER 1 Introduction 1
1.1 MOTIVATION 2
1.2 OVERVIEW 5
1.3 THESIS ORGANIZATION 8
CHAPTER 2 Overall of the Proposed that the
ROI of Rice Planthopper by Image
Processing 9
2.1 IMAGE PREPROCESSING AND SET ROI 12
2.1.1. Image preprocessing 12
2.1.2. Set ROI 14
2.2 COLOR ANALYSIS AND CLASSIFICATION 17
2.2.1. Color analysis 17
2.2.2. Classification 20
2.3 ADD NIR IMAGE TO CLASSIFY 20
2.4 MARK RPHS 24
CHAPTER 3 Experimental Results 28
CHAPTER 4 Conclusion 41
CHAPTER 5 Acknowledgment 43
REFERENCES 45

[1] 黃守宏， 鄭清煥， 陳秋男， 吳文哲”台灣水稻害蟲發生趨勢與防治展望”,台灣水稻保護成果及新展望研討會專刊:, 2009, 131-147.
[2] http://hello.area.com.tw/is_cn.cgi?areacode=nt097&ID=cn-j53-36
[3] Jingfu, Li; Zhijun, "Long. Study on agriculture image processing based on discrete wavelet transform", In: Geoscience and Remote Sensing (IITA-GRS), 2010 Second IITA International Conference on. IEEE, 2010. p. 384-387
[4] Liu, Xin, et al. "Applications of perceptual hash algorithm in agriculture images", In: Image and Signal Processing (CISP), 2013 6th International Congress on. IEEE, 2013. p. 698-702.
[5] Mustafa, Nur Badariah Ahmad, et al. "Image processing of an agriculture produce: Determination of size and ripeness of a banana." In: Information Technology, 2008. ITSim 2008. International Symposium on. IEEE, 2008. p. 1-7.
[6] Suksawat, Bandit; Komkum, Preecha. "Pineapple quality grading using image processing and fuzzy logic based on Thai Agriculture Standards." In: Control, Automation and Robotics (ICCAR), 2015 International Conference on. IEEE, 2015. p. 218-222.
[7] Shivani K. Tichkule; Dhanashri. H. Gawali. "Plant diseases detection using image processing techniques." Green Engineering and Technologies (IC-GET), 2016, Nov.
[8] N. Mongkolchart, and M. Ketcham, "The measurement of brown planthopper by image processing", Int'l Conference on Advanced Computational Technologies & Creative Media (ICACTCM 2014),August 2014.
[9] S. Watcharabutsarakham, I. Methasate, N. Watcharapinchai, W. Sinthupinyo and W. Sriratanasak, "An approach for density monitoring of brown planthopper population in simulated paddy fields", IEEE Computer Science and Software Engineering (JCSSE), July 2016.
[10] Y. Qing, X. Ding-xiang, L. Qing-jie, Y. Bao-jun, D. Guang-quiang and T. Jian, "Automated counting of rice planthoppers in paddy fields based on image processing", Journal of Integrative Agriculture, 13(8), August 2014, p.1736-1745.
[11] S. Cochrane, "The Munsell Color System: A scientific compromise from the world of art" Studies in History and Philosophy of Science Part A, vol. 27, June 2014, pp. 26-41.
[12] Smith, Alvy Ray. "Color gamut transform pairs." ACM Siggraph Computer Graphics 12.3 (1978): 12-19.
[13] L. Brun and A. Trémeau, "Color quantization, " Digital Color Imaging Handbook, 2003, p.589-638.
[14] J. R. Quinlan, "Induction of decision trees. " Machine learning 1, 1986, p. 81-106.
[15] Bailey, Donald G., and Christopher T. Johnston. "Single pass connected components analysis." Proceedings of image and vision computing New Zealand. 2007.