請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/81780完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 陳世銘(Suming Chen) | |
| dc.contributor.author | Yi-Jing Wu | en |
| dc.contributor.author | 吳怡靜 | zh_TW |
| dc.date.accessioned | 2022-11-25T03:03:26Z | - |
| dc.date.available | 2024-08-23 | |
| dc.date.copyright | 2021-11-11 | |
| dc.date.issued | 2021 | |
| dc.date.submitted | 2021-08-23 | |
| dc.identifier.citation | 一丞通訊。1999。水果與堅果冷藏過程中之褐變研究。VOL.43。 王啟維。2011。以螢光影像技術檢測蘋果之褐變。碩士論文。台北:國立臺灣大學生物產業機電工程學研究所。 李睿芝。2016。螢光光譜影像檢測技術於萵苣受大腸桿菌汙染之應用。碩士論文。台北:國立臺灣大學生物產業機電工程學研究所。 陳世銘、馮丁樹、張家禎。1995。番茄與柑橘共用型顏色選別指標之研究。農業機械學刊 4(4):47-57。 許涵竣。2017。蝴蝶蘭開花品質之光譜預測模式。碩士論文。台北:國立臺灣大學生物產業機電工程學研究所。 黃至勝。2018。機器學習\統計方法: 模型評估-驗證指標(validation index)。網址: https://chih-sheng-huang821.medium.com/%E6%A9%9F%E5%99%A8%E5%AD%B8%E7%BF%92-%E7%B5%B1%E8%A8%88%E6%96%B9%E6%B3%95-%E6%A8%A1%E5%9E%8B%E8%A9%95%E4%BC%B0-%E9%A9%97%E8%AD%89%E6%8C%87%E6%A8%99-b03825ff0814。上網時間: 2021-05-01。 劉執中。2016。以高光譜影像技術檢測稻米新鮮度之研究。碩士論文。台北:國立臺灣大學生物產業機電工程學研究所。 謝騄璘。2006。飽和脈衝葉綠素螢光影像系統之建立及於植物光熱逆境生理之應用。碩士論文。台北:國立臺灣大學生物產業機電工程學研究所。 蕭世傑。2011。以多通道螢光光譜影像系統與螢光指標探討甘藍苗水份逆境之研究。博士論文。台北:國立臺灣大學生物產業機電工程學研究所。 簡佑佳。2014。應用螢光光譜指紋技術檢測食用生菜污染之研究。碩士論文。台北:國立臺灣大學生物產業機電工程學研究所。 Baker, N., and E. Rosenqvist. 2004. Applications of chlorophyll fluorescence can improve crop production strategies: an examination of future possibilities. Journal of Experimental Botany 55(403): 1607-1621. Banks, N., and M. Joseph. 1991. Factors affecting resistance of banana fruit to compression and impact bruising. Journal of the Science of Food and Agriculture 56(3): 315-323. Behera, S. K., A. K. Rath, and P. K. Sethy. 2020. Maturity status classification of papaya fruits based on machine learning and transfer learning approach. Information Processing in Agriculture. Available online 20 May 2020 in press. Bolhar-Norderkampf, H. R., and G. Oquist. 1993. Chlorophyll fluorescence as a tool in photosynthesis research. In “Photosynthesis and Production in a Changing Environment: A Field and Laboratory Manual”. eds. D. O. Hall, J. M. O. Scurlock, H. R. Bolhar-Norderkampf, R. C. Leegood, and S. P. Long, 193-206. New York: Chapman and Hall. Buschmann, C. and H. K. Lichtenthaler. 1997. Principles and characteristics of multi-colour fluorescence imaging of plants2. Journal of Plant Physiology 152(2-3): 297-314. Buschmann, C., G. Langsdorf, and H. K. Lichtenthaler. 2000. Imaging of the blue, green, and red fluorescence emission of plants: an overview. Photosynthetica 38(4): 483-491. Chappelle, E. W., F. M. Wood, J. E. Mcmurtrey, and W. W. Newcourt. 1985. Laser-induced fluorescence of green plants. 3: LIF spectral signatures of five major plant types. Appl. Optics 24:74-80. Chappelle, E. W., E. J. MCMurtrey III, and M. S. Kim. 1991. Identification of the pigment responsible for the blue fluorescence band in the laser induced fluorescence (LIF) spectra of green plants, and the potential use of this band in remotely estimating rates of photosynthesis. Remote Sensing of Environment 36(3): 213-218 Chiu, Y. C., X. L. Chou, T. E. Grift, and M. T. Chen. 2015. Automated detection of mechamically induced bruise areas in golden delicious apples using fluorescence imagery. Transactions of the ASABE 58(2): 215-225. Chiu, Y. C., and C. H. Chen. 2017. Development of on-line apple bruise detection system. Engineering in Agriculture, Environment and Food 10(3): 223-232. Dubey, S. R., and A. S. Jalal. Apple disease classification using color, texture and shape features from images. 2016. Signal, Image and Video Processing 10 : 819-826. Franck, C., J. Lammertyn, Q. T. Ho, P. Verboven, B. Verlinden, and B. M. Nicolaï. Browning disorders in pear fruit. Postharvest Biology and Technology. 43(1):1-13. Fujita, K., M. Tsuta, M. Kokawa, and J. Sugiyama. 2010. Detection of Deoxynivalenol Using Fluorescence Excitation–Emission Matrix. Food and Bioprocess Technology 3(6):922-927. Garcia, J., M. Ruiz-Altisent, and P. Barreiro. 1995. Factors influencing mechanical properties and bruise susceptibility of apples and pears. Journal of Agricultural Engineering Research 61(1): 11-18. Girshick R., J. Donahue, T. Darrell, and J. Malik. 2014. Rich feature hierarchies for accurate object detection and semantic segmentation. In “Conference on Computer Vision and Pattern Recognition 2014 (CVPR 2014)”. pp. 580-587. USA: Greater Columbus Convention Center, Ohio. Hamamatsu. 2006. Photomultiplier tubes R3788, R4332. Available at: http://www.google.com.tw/url?sa=t rct=j q= esrc=s source=web cd=1 ved=0CCQQFjAA url=http%3A%2F%2Fwww.hamamatsu.com%2Fresources%2Fpdf%2Fetd%2FR3788_R4332_TPMS1021E02.pdf ei=4WCYU9qJL8KxlQXlyoHAAg usg=AFQjCNFZXDuvf7JofnGUJBRQfu6DVjTpHw. Accessed: 29 Sep. 2020. Hsiao, S. C., S. Chen, I. C. Yang, C. T. Chen, C. Y. Tsai, Y. K. Chuang, F. J. Wang, T. S. Lin, and Y. M. Lo. 2010. Evaluation of plant seedling water stress using dynamic fluorescence index with blue LED-based fluorescence imaging. Computer and Electronics in Agriculture 72:127-133. Jasco. 2020. FP-8300 Spectrofluorometer. Available at: https://jascoinc.com/products/spectroscopy/fluorometer/spectrofluorometer-models/fp-8350-spectrofluorometer/. Accessed: 29 Sep. 2020. Jackson, J. E. 1991. A user's guide to principal components. Wiley series in probability and mathematical statistics. Wiley, New York. Jiang, Y., and X. Duan and S. Zheng. 2016. Browning: Enzymatic Browning. In “Encyclopedia of Food and Health”, ed. B. Caballero, P. M. Finglas and F. Toldrá, 508-514. Englan:Academic Press. Jiang, M., Y. Rao, J. Zhang, and Y. Shen. 2020. Automatic behavior recognition of group-housed goats using deep learning. Computers and Electronics in Agriculture. Vol. 177.3 Kautsky H, W. Appel, and H. Amann. 1960. Chlorophyllfluorescenz und kohlensaureassimilation. Biochemische Zeitschrift322: 277–292. Kim, M., Y. Chen, and P. M. Mehl. 2001. Hyperspectral reflectance and fluorescence imaging system for food quality and safety. Transactions of the ASAE 44(3): 721-729. Krizhevsky, A., I. Sutskever, and G.H. Hinton. 2012. ImageNet classification with deep convolutional neural networks. In” Advances in Neural Information Processing Systems 25(NIPS 2012)”, eds. F. Pereira and C. J. C. Burges and L. Bottou and K. Q. Weinberger. USA: Lake Tahoe, Nevada. Knee, M. and A. R. Miller. 2002. Mechanical injury. In” Fruit Quality and its Biological Basis” ed. M. Knee, 157-179. UK: Sheffield Academic Press. LISA Lab. 2013. Convolutional Neural Networks (LeNet) - DeepLearning 0.1 documentation. Available at: http://deeplearning.net/tutorial/lenet.html. Accessed: 29 Sep. 2020. Liu H., Y. Saito, D. F. Al Riza, N. Kondo, X. Yang, and D. Han. 2019. Rapid evaluation of quality deterioration and freshness of beef during low temperature storage using three-dimensional fluorescence spectroscopy. Journal of Food Chemistry. 287:369-374. Lozano, J. E. 2006. Fruit Manufacturing. 163-182. Argentina: Springer. Mahlein, K., C. Oerke, U. Steiner, and W. Dehne. 2012. Recent advances in sensing plant diseases for precision crop protection. European Journal of Plant Pathology 133(1):197-209. Momin, M. A., N. Knodo, Y. Ogawa, T. Shiigi, M. Kurita, and K. Ninomiay. 2010. Machine Vision System for Detecting Fluorescent Area of Citrus Using Fluorescence Image. IFAC Proceedings Volumes 43(26):241-244 Persic, M., M. Mikulic-Petkovsek, A. Slantnar, and R. Veberic. 2017. Chemical composition of apple fruit, juice and pomace and the correlation between phenolic content, enzymatic activity and browning. LWT-Food Science and Technology 82:23-31. Redmon J., S. Divvala, R. Girshick, and A. Farhadi. 2016. You Only Look Once: Unified, Real-Time Object Detection. In “Conference on Computer Vision and Pattern Recognition 2016 (CVPR 2016)”. pp. 779-788. USA: Caesar's Palace, Las Vegas. Saito, Y., M. Kanoh, K. Hatakw, T. D. Kawahara, and A. Nomura. 1998. Investigation of laser-induced fluorescence of several natural leaves for application to lidar vegetation monitoring. Appl. Optics 37(3): 431-437. Sommano, S. R., U. Chanasut, and W. Kumpoun. 2020. Enzymatic browning and its amelioration in fresh-cut tropical fruits. In “Fresh-Cut Fruits and VegetablesTechnologies and Mechanisms for Safety Control”, ed. M. W. Siddiqui, 51-76. Englan:Academic Press. Thomas, J., and H. Nijhuis. 1968. Relative stability of chlorophyll complexes in vivo. Biochimica et Biophysica Acta (BBA)-Bioenergetics 153(4): 868-877. Tian Y., G. Yang, Z. Wang, E. Li, and Z. Liang. 2019. Detection of apple lesions in orchards based on deep learning methods of CycleGAN and YOLOV3-Dense. Journal of Sensors. Article ID 7630926. Weaver, C. and H. Charley. 1974. Enzymatic browning of ripening bananas. Journal of Food Science 39:1200-1202. Zude, M. 2003. Detection of Fruit Tissue Browning Using Laser-Induced Fluorescence Spectroscopy. ISHS Acta Horticulturae 628(8): 85-91. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/81780 | - |
| dc.description.abstract | 內部成分中含有酚類化合物之水果在採收後若沒有適當的保存或是遭受外力撞擊,會因內部成分發生化學變化而降低品質。酵素型褐變是因內部產生不可逆的化學變化使果皮或果肉的顏色轉變為黑褐色,因此若能在銷售前將已產生褐變的水果篩選出來,便能保障消費者權益並提升商品品質。本研究以螢光光譜資訊結合影像利用深度學習之分析方法對螢光影像進行分類,與傳統機器學習演算法之分析結果進行比較,並且利用智慧影像偵測之模型對樣本之彩色影像進行褐變位置之偵測,以達到非破壞且即時的檢測效果。 本研究所用的實驗樣本為美國青蘋果(Granny Smith),使用螢光光譜儀量測青蘋果褐變前後之螢光強度變化,並分析找出特徵激發光與放射光波長,用來建置高光譜螢光影像系統,探討出使用365 nm之激發光源可以在560 nm與670 nm有相關螢光反應。使用高光譜螢光影像系統拍攝在特徵波長下青蘋果褐變前後之螢光影像,並以CNN分類模型進行分類及預測,比較兩種特徵波長在有沒有暗處理下之影像分類結果,最終以混淆矩陣比較CNN模型之驗證準確率,以560 nm螢光影像之準確率高於670 nm螢光影像。 使用高光譜螢光影像系統拍攝青蘋果樣本褐變前後之全波段(450 nm ~ 700 nm)螢光影像,利用自行開發之影像處理程式取得樣本褐變前後在不同波長下相對應之平均螢光強度值,使用PCA分析將原始26維度之資訊降維至前五個主成分累積變異數達到99.3%,再以KNN模型對降維後之數據進行分類及預測,達到驗證準確率92.11%。 使用自製打光室與影像擷取系統,拍攝撞擊後之青蘋果彩色影像,並建立RCNN與YOLOv4兩套物件偵測模型對彩色影像進行褐變位置之偵測,統計偵測結果並建立該模型之混淆矩陣,藉由模型指標F1-Score來判斷該模型之準確率與精準度。RCNN模型之F1-Score值為24.3%,而YOLOv4模型之F1-Score值為97.1%,最終青蘋果影像以YOLOv4模型對褐變位置之偵測結果最好。綜合三項實驗結果在酵素型褐變之螢光變化特性在CNN分類模型上可以得到比葉綠素螢光影像更好的結果,使用螢光影像訓練深度學習模型可以較傳統機器學習演算法有更完整的特徵提取以達到好的分類效果,另外使用彩色影像進行褐變位置偵測也能獲得不錯的驗證準確率。 | zh_TW |
| dc.description.provenance | Made available in DSpace on 2022-11-25T03:03:26Z (GMT). No. of bitstreams: 1 U0001-2208202120521500.pdf: 4058324 bytes, checksum: 7f0f2c875474a0ac0e1f530a3439c5a9 (MD5) Previous issue date: 2021 | en |
| dc.description.tableofcontents | "口試委員審定書 i 致 謝 ii 摘 要 iv Abstract vi 圖目錄 xii 表目錄 xv 第一章 前 言 1 1.1 研究動機 1 1.2 研究目的 2 第二章 文獻探討 3 2.1 水果褐變 3 2.1.1 酵素型褐變 3 2.1.1.1 物理傷害產生之褐變 4 2.2 植物的螢光反應 4 2.2.1 葉綠素螢光 5 2.2.2 其他非葉綠素螢光 7 2.3 螢光光譜檢測技術 8 2.3.1 葉綠素螢光指標檢測 8 2.3.2 螢光光譜指紋檢測 10 2.4 光譜影像技術與應用 12 2.4.1 高光譜影像檢測技術 13 2.4.2 螢光光譜影像檢測技術 15 2.5 智慧影像檢測與辨識 16 2.5.1 智慧影像應用於農業 16 第三章 材料與方法 18 3.1 樣本選擇與處理 18 3.1.1 樣本來源 19 3.1.2 樣本褐變處理 19 3.1.2.1 螢光光譜儀試驗之樣本褐變處理 19 3.1.2.2 螢光高光譜影像試驗之樣本褐變處理 20 3.2 實驗儀器設備 23 3.2.1 螢光光譜儀試驗之儀器設備 23 3.2.2 高光譜螢光影像系統 25 3.2.3 彩色影像擷取系統 26 3.3 實驗流程 28 3.3.1 螢光光譜儀試驗 29 3.3.2 高光譜螢光影像擷取(褐變特徵波段) 30 3.3.3 高光譜螢光影像擷取(全波段)與彩色影像擷取 32 3.4 數據處理 32 3.4.1 螢光光譜儀數據之處理 33 3.4.2 螢光影像之校正處理 35 3.4.2.1 激發光源之雜訊校正 36 3.4.2.2 暗電流校正與平場校正 37 3.4.2.3 消除雜訊 38 3.4.2.4 影像裁切(褐變特徵波段) 38 3.4.2.5 製作遮罩(全波段螢光影像) 39 3.5 螢光數據檢測分析方法 40 3.5.1 螢光光譜儀試驗之分析 40 3.5.1.1 馬氏距離(Mahalanobis distance, MD) 40 3.5.2 高光譜螢光影像之分析(褐變特徵波段) 41 3.5.2.1 卷積神經網絡(Convolutional neural network, CNN) 41 3.5.2.2 混淆矩陣(Confusion Matrix) 43 3.5.3 高光譜螢光影像之分析(全波段) 44 3.5.3.1 主成分分析(principal component analysis, PCA) 44 3.5.3.2 KNN(K Nearest Neighbor)演算法 45 3.5.4 彩色影像之分析 45 3.5.4.1 RCNN (Region Convolution Neural Network)辨識模型建立 45 3.5.4.2 YOLOv4 (You Only Look Once v4)辨識模型建立 48 第四章 結果與討論 51 4.1 螢光光譜儀試驗結果 51 4.1.1 青蘋果褐變特徵螢光光譜 51 4.1.2 青蘋果葉綠素螢光光譜 52 4.1.3 馬氏距離分析結果 53 4.1.3.1 青蘋果褐變特徵螢光波段 54 4.1.3.2 青蘋果葉綠素螢光波段 55 4.2 高光譜螢光影像檢測結果(褐變特徵螢光波段) 57 4.2.1 高光譜螢光影像校正與處理的結果 57 4.2.2 特徵波段螢光影像有無暗處理與不同型態之呈現 59 4.2.3 CNN分類及預測準確率比較結果 61 4.3 高光譜螢光影像檢測結果(全波段) 69 4.3.1 全波段高光譜螢光影像校正與處理結果 69 4.3.2 PCA數據降維後之KNN分類結果 69 4.4 彩色影像褐變位置檢測結果 71 4.4.1 RCNN模型辨識結果 71 4.4.2 YOLO v4 模型辨識結果 73 第五章 結論 76 參考文獻 78 " | |
| dc.language.iso | zh-TW | |
| dc.subject | 酵素型褐變 | zh_TW |
| dc.subject | 深度學習 | zh_TW |
| dc.subject | 物件偵測 | zh_TW |
| dc.subject | 螢光影像 | zh_TW |
| dc.subject | 葉綠素螢光 | zh_TW |
| dc.subject | enzyme browning | en |
| dc.subject | object detection | en |
| dc.subject | deep learning | en |
| dc.subject | chlorophyll fluorescence | en |
| dc.subject | fluorescence image | en |
| dc.title | 以螢光高光譜影像智慧檢測蘋果褐變之研究 | zh_TW |
| dc.title | Intelligent Detection of Apple Browning by Hyperspectral Fluorescence Imaging | en |
| dc.date.schoolyear | 109-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 艾群(Hsin-Tsai Liu),邱奕志(Chih-Yang Tseng),蕭世傑,楊宜璋 | |
| dc.subject.keyword | 螢光影像,酵素型褐變,葉綠素螢光,深度學習,物件偵測, | zh_TW |
| dc.subject.keyword | fluorescence image,enzyme browning,chlorophyll fluorescence,deep learning,object detection, | en |
| dc.relation.page | 79 | |
| dc.identifier.doi | 10.6342/NTU202102594 | |
| dc.rights.note | 同意授權(全球公開) | |
| dc.date.accepted | 2021-08-24 | |
| dc.contributor.author-college | 生物資源暨農學院 | zh_TW |
| dc.contributor.author-dept | 生物機電工程學系 | zh_TW |
| dc.date.embargo-lift | 2024-08-23 | - |
| 顯示於系所單位: | 生物機電工程學系 | |
文件中的檔案:
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| U0001-2208202120521500.pdf | 3.96 MB | Adobe PDF | 檢視/開啟 |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。
