臺灣博碩士論文加值系統

根系吸收土壤中的水分與礦物質供植物體維持正常的生理功能，環境改變時根系亦為植物展現抗鹽、抗旱能力的主要器官。水稻(Oryza sativa L.)擁有多樣的原生品系與馴化品種，各自適應不同的鹽度與水分等土壤條件。然而，地表下的根系的形態特徵是否與水稻的抗鹽、抗旱能力有關，一直是水稻育種研究的重要議題。本研究目的為發展量測水稻根系特徵的影像系統並量測15個品種之水稻幼苗根系形態特徵，首先使用相機拍攝種植在組織培養基中二維水稻根系側視影像，接著以卷積神經網路(Convolutional neural network)進行影像辨識來獲得完整的根系剪影(Silhouette)，透過空間切割(Space-carving)演算法，重建根系的三維影像，並從三維影像中量化根系之形態特徵，最後以地面真相(Ground truth)測試系統準確度。本研究最終量化出15個品種的水稻幼苗根系形態特徵以供水稻育種之根系表現型研究的應用。

Roots are important organs of plants. Root system architecture (RSA), the spatial configuration of roots, of rice (Oryza sativa L.) has shown a high degree of diversity. RSA needs to be quantified with high accuracy to understand the relationship between RSA and functionality of rice roots. This study developed a three-dimensional (3D) imaging system to quantify the RSA of rice seedling roots of 15 varieties. In this work, rice seedlings were cultivated in glass tubes filled with transparent jelly culture medium for ten days. The two-dimensional (2D) side-view images of the seedlings were acquired using the imaging system. Silhouettes of rice roots were then identified from the 2D side-view images using image recognition technology. Three-dimensional images of the rice roots were next reconstructed using the silhouettes and space-carving algorithm. A ground truth was used to validate the accuracy of the system. Last, RSA traits of rice seedling root of 15 varieties were quantified.

ACKNOWLEDGEMENTS i
摘要 ii
ABSTRACT iii
LIST OF FIGURES vi
LIST OF TABLES viii
CHAPTER 1. INTRODUCTION 1
1.1 General Background Information 1
1.2 Objectives 1
1.3 Organization 2
CHAPTER 2. LITERATURE REVIEW 3
2.1. Importance of study RSA with 3D image 3
2.2. Three-dimensional reconstruction algorithm 3
2.3. Research of seedling root in 3D 4
CHAPTER 3. MATERIALS AND METHODS 5
3.1. Sample preparation 5
3.2. Imaging system development 7
3.3. Background removal using CNN 9
3.4. 3D root model reconstruction 10
3.5. Traits quantification 12
3.6. Accuracy validation 15
CHAPTER 4. RESULTS AND DISCUSSION 17
4.1. Image after background removal 17
4.2. 3D model of seedling root 18
4.3. Phenotypic traits of 15 varieties 19
4.4. Accuracy of system 22
CHAPTER 5. CONCLUSION 24
REFERENCES 25

Armengaud, P., Zambaux, K., Hills, A., Sulpice, R., Pattison, R. J., Blatt, M. R., & Amtmann, A. (2009). EZ-Rhizo: integrated software for the fast and accurate measurement of root system architecture. Plant Journal, 57(5), 945-956.
Casimiro, I., Marchant, A., Bhalerao, R. P., Beeckman, T., Dhooge, S., Swarup, R., ... & Bennett, M. (2001). Auxin transport promotes Arabidopsis lateral root initiation. The Plant Cell, 13(4), 843-852.
Clark, R. T., Famoso, A. N., Zhao, K. Y., Shaff, J. E., Craft, E. J., Bustamante, C. D., Kochian, L. V. (2013). High-throughput two-dimensional root system phenotyping platform facilitates genetic analysis of root growth and development. Plant Cell and Environment, 36(2), 454-466.
Clark, R. T., MacCurdy, R. B., Jung, J. K., Shaff, J. E., McCouch, S. R., Aneshansley, D. J., & Kochian, L. V. (2011). Three-dimensional root phenotyping with a novel imaging and software platform. Plant physiology, 156(2), 455-465.
Dijkstra, E. W. (1959). A note on two problems in connexion with graphs. Numerische mathematik, 1(1), 269-271.
Geiger, A., Ziegler, J., & Stiller, C. (2011). Stereoscan: Dense 3d reconstruction in real-time. In Intelligent Vehicles Symposium (IV), 2011 IEEE (pp. 963-968). Ieee.
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems (pp. 1097-1105).
Kutulakos, K. N., & Seitz, S. M. (1999). A theory of shape by space carving. In Computer Vision, 1999. The Proceedings of the Seventh IEEE International Conference on (Vol. 1, pp. 307-314). IEEE.
Kumar, P., Cai, J., & Miklavcic, S. (2013). 3D reconstruction, modelling and analysis of in situ root system architecture. In 20th International Congress on Modelling and Simulation (pp. 517-523).
Lam, L., Lee, S. W., & Suen, C. Y. (1992). Thinning methodologies-a comprehensive survey. IEEE Transactions on pattern analysis and machine intelligence, 14(9), 869-885.
Lobet, G., Pages, L., & Draye, X. (2011). A Novel Image-Analysis Toolbox Enabling Quantitative Analysis of Root System Architecture. Plant Physiology, 157(1), 29-39.
Naeem, A., French, A. P., Wells, D. M., & Pridmore, T. P. (2011). High-throughput feature counting and measurement of roots. Bioinformatics, 27(9), 1337-1338.
Topp, C. N., Iyer-Pascuzzi, A. S., Anderson, J. T., Lee, C. R., Zurek, P. R., Symonova, O., ... & Moore, B. T. (2013). 3D phenotyping and quantitative trait locus mapping identify core regions of the rice genome controlling root architecture. Proceedings of the National Academy of Sciences, 110(18), E1695-E1704.
Vosselman, G., & Dijkman, S. (2001). 3D building model reconstruction from point clouds and ground plans. International archives of photogrammetry remote sensing and spatial information sciences, 34(3/W4), 37-44.