台灣的水果豐富多樣，除了自給自足外，外銷市場也是不容小覷，因此水果的分級是相當重要的，現今大多使用人工目測將水果依照外觀品質做分級，除了處理成本高之外，每個人主觀判別的標準也不依，因此本研究利用MATLAB撰寫處理程式，開發以影像辨識番石榴外觀的非破壞性品質檢測應用程式，目的在於將水果快速且有系統地分級，根據蒐集樣本設定特徵值，並找出判斷番石榴外部品質之標準。同時也探討拍攝番石榴樣本的實驗環境，實驗結果顯示在白色背景的自然光下所拍攝的初始影像，去除背景及影像辨識的效果相較於其他環境較佳，運用影像處理技術找出番石榴的特徵值，最後將判斷結果彙整成Excel紀錄表單，讓使用者能快速檢視缺點區域百分比，其經系統實際測量後，此辨識系統平均每判斷一張影像需花費4秒時間。除了提供農民一種快速檢測水果分級缺點的參考標準，而缺點的特徵值設定，可彈性地依據使用者的判別標準提高或降低特徵值，以達辨識分級的目的。提供消費者值得信賴的好品質，建立與塑造品牌蔬果形象，創造優質精緻化農業。

Taiwan's fruits are rich and diverse. In addition to being self-sufficient, the export market is also not to be underestimated. Therefore, the classification of fruits is very important. Today, most people use manual visual inspection to classify fruits according to their appearance quality. In addition to high processing costs, everyone is subjective. Discrimination standards are not adhered to, so this research uses MATLAB to write a processing program to develop a non-destructive quality detection application that uses the image to identify the appearance of guava. The purpose is to quickly and systematically classify fruits, set characteristic values based on collected samples, and Find out the criteria for judging the external quality of guava. At the same time, the experimental environment for taking guava samples is also discussed. The experimental results show that the initial image was taken under natural light with a white background, the effect of removing the background and image recognition is better than other environments. Use image processing technology to find out the guava's Feature values, and finally, the judgment results are aggregated into an Excel record form, allowing users to quickly view the percentage of defective areas. After the system actually measures, the recognition system takes an average of 4 seconds to judge each image. In addition to providing a reference standard for farmers to quickly detect the shortcomings of fruit grading, the characteristic value setting of the shortcomings can flexibly increase or decrease the characteristic value according to the user's discrimination criteria to achieve the purpose of identifying and grading. Provide consumers with trusted good quality, establish and shape the brand's image of fruits and vegetables, and create high-quality and refined agriculture.

參考文獻
中文部分
1.王至誠(民107)。基於圖像識別技術的電子元器件分類。電腦編程技巧與維護，1，142-147。
2.張佑瑋(民94)。自動灰階影像上色系統。台灣科技大學資訊管理系，碩士論文。
3.王維、宋雪樺(民106)。基於動態閾值的彩色圖像邊緣檢測與分析。信息技術，8，204-207。
4.王慶平、郭思哲、和麗芳、李濤(民105)。手勢識別圖像匹配技術的研究與應用。價值工程，19，185-187。
5.王曉楠、伍萍輝、馮青春、王國華(民105)。番茄採摘機器人系統設計與試驗。農機化研究，4，94-98。
6.冷建偉、沈芳婷(民106)。基於HSV顏色模型和區域生長算法的水文圖像分割。計算機工程期刊，7，223-228。
7.李柔靜、陳世銘、陳毓良、邱奕志、杜威霆、潘姵如(民105)。番茄採收機器人視覺系統之研究。農業機械學刊，24，1-12。
8.林道通(譯)(民 108)。數位影像處理(原作者：Alasdair McAndrew)。高立圖書有限公司。
9.姚敏、牟雪兒、陳鵬、趙夢龍、栗卓然(民107)。圖像中印章的檢測定位與識別研究。信息技術與信息化，12，148-150。
10.張靜、葉玉堂、謝煜、常永鑫、劉霖、劉娟秀、羅穎、葉溯(民104)。印刷電路板外觀檢測光電圖像色度校正方法。計量學報，3，238-241。
11.郭晶晶、李慶武、程海粟、仇春春(民105)。基於Lab顏色距離和GMM的樹木圖像分割算法。信息技術，2，1-4。
12.陳奇中(民106)。MATLAB程式設計與工程應用。東華書局。
13.黃登淵、莊國禎、楊晏和、陳南樺、王嘉宏(民96)。複雜背景下多重人臉偵測演算法之研究。科學與工程技術期刊，3，35-43。
14.黃膺任、李芳繁(民86)。使用影像處理進行棗子分級之研究。農業機械學刊，2，15-23。
15.寧紀鋒、何東健、張海亮、龍滿生(民90)。基於圖像形態學的球形果實品質檢測研究。農機械化研究，3，28-30。
16.趙宏宇、肖創柏、禹晶、白鷺(民103)。一種用於MRF夜間彩色圖像增強的Retinex算法。光學精密工程期刊，4，1048-1055。
17.趙亞、王震洲(民106)。基於數字圖像處理的pH試紙自動檢測技術。機械與電子期刊，7，56-59。
18.趙青青、張濤、鄭偉波(民105)。基於空間培養的植物圖像處理方法。傳感器與微系統，10，46-48。
19.劉玉山(民107)。商管教育的新視野：朝向一個整合大數據、人工智能、移動運算與雲端服務的思維架構。東亞論壇季刊，498，1-7。
20.歐秀明(民97)。應用色彩學。雄獅圖書。
21.衛祖賞(民71)。數位影像處理。全華圖書。
22.戴孟宗(民106)。現代色彩學。全華出版。
23.繆紹綱(民97)。數位影像處理。培生教育。
24.謝青霖、馮丁樹、陳世銘(民81)。數位影像處理在蔬果大小選別之應用。農業機械學刊，1，28-41。
英文部分
1.Alotaibi, M., Mahmood, A. (2017) Improved gait recognition based on specialized deep convolutional neural network. Understanding, 164, 103-110.
2.Bjorklund, T., Fiandrotti, F. D., Annarumma, M., Francini, G. (2019) Robust license plate recognition using neural networks trained on synthetic images. Pattern Recognition, 93, 134-146.
3.Jimenez, E. L., Juan Irving Vasque Gomeza, J. I. V., Acevedo, M. A. S., Lozada, J. C. H., Arcia, A. V. U. (2019) Columnar cactus recognition in aerial images using a deep learning approach. Ecological Informatics, 52, 131-138.
4.Knapik, M., Cyganek B. (2019) Driver’s fatigue recognition based on yawn detection in thermal images. Neurocomputing, 338, 274-292.
5.Lee, H. H., Hong, K. S. (2017) Automatic recognition of flower species in the natural environment. Image and Vision Computing, 61, 98-114.
6.Li, J. X., Zhang, D. X., Zhang, J. J., Zhang, J., Li, T., Xia, Y., Yan, Q., Lina, X. (2017) Facial Expression Recognition with Faster RCNN. Procedia Computer Science, 107, 135-140.
7.Shustanov, A., Yakimova, P. (2017). CNN Design for Real Time Traffic Sign Recognition. Procedia Engineering, 201, 718-725 .
8.Tsai, D. M., Chen, W. L. (2017). Coffee plantation area recognition in satellite images using Fourier transform. Computers and Electronics in Agriculture, 135, 115-127.
9.Uddin, M. Z., Hassan, M. M., Almogren, A., Zuair, M., Fortino, G., Torresen, J. (2017) A facial expression recognition system using robust face features from depth videos and deep learning. Computers & Electrical Engineering, 63, 114-125.
10.Wang, S.F., Gan, Q., Ji, Q. (2017) Expression-assisted facial action unit recognition under incomplete AU annotation. Pattern Recognition, 61, 78-91.
11.Xiang, R. (2018) Image segmentation for whole tomato plant recognition at night. Computers and Electronics in Agriculture, 154, 434-442.
12.You, W., Zhou, W., Huang, J., Yang, F., Liu, Y. Q., Chen, Y. E. (2019) A bilayer image restoration for finger vein recognition. Neurocomputing, 348, 54-65.
13.Zhang, S. W., Wu, X. W., You, Z.H., Zhang, L.Q. (2017) Leaf image based cucumber disease recognition using sparse representation classification. Computers and Electronics in Agriculture, 134, 135-141