Plant segmentation by supervised machine learning methods

High‐throughput phenotyping systems provide abundant data for statistical analysis through plant imaging. Before usable data can be obtained, image processing must take place. In this study, we used supervised learning methods to segment plants from the background in such images and compared them with commonly used thresholding methods. Because obtaining accurate training data is a major obstacle to using supervised learning methods for segmentation, a novel approach to producing accurate labels was developed. We demonstrated that, with careful selection of training data through such an approach, supervised learning methods, and neural networks in particular, can outperform thresholding methods at segmentation.

[1]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[2]  Christian Klukas,et al.  Integrated Analysis Platform: An Open-Source Information System for High-Throughput Plant Phenotyping1[C][W][OPEN] , 2014, Plant Physiology.

[3]  Sida I. Wang,et al.  Dropout Training as Adaptive Regularization , 2013, NIPS.

[4]  D. Ruppert.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction , 2004 .

[5]  Guilherme J. M. Rosa.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction by HASTIE, T., TIBSHIRANI, R., and FRIEDMAN, J , 2010 .

[6]  Falk Schreiber,et al.  HTPheno: An image analysis pipeline for high-throughput plant phenotyping , 2011, BMC Bioinformatics.

[7]  Chih-Jen Lin,et al.  A Practical Guide to Support Vector Classication , 2008 .

[8]  Ryan F. McCormick,et al.  3D Sorghum Reconstructions from Depth Images Identify QTL Regulating Shoot Architecture1[OPEN] , 2016, Plant Physiology.

[9]  Bülent Sankur,et al.  Survey over image thresholding techniques and quantitative performance evaluation , 2004, J. Electronic Imaging.

[10]  Chenyong Miao,et al.  Optimising the identification of causal variants across varying genetic architectures in crops , 2018, bioRxiv.

[11]  E. R. Davies.  Computer and Machine Vision: Theory, Algorithms, Practicalities , 2012 .

[12]  Charles E. Heckler,et al.  Applied Multivariate Statistical Analysis , 2005, Technometrics.

[13]  Malia A. Gehan,et al.  Lights, camera, action: high-throughput plant phenotyping is ready for a close-up. , 2015, Current opinion in plant biology.

[14]  Philippe Lucidarme,et al.  On the use of depth camera for 3D phenotyping of entire plants , 2012 .

[15]  Andy Lin,et al.  PlantCV v2: Image analysis software for high-throughput plant phenotyping , 2017, PeerJ.

[16]  Yi Lin,et al.  LiDAR: An important tool for next-generation phenotyping technology of high potential for plant phenomics? , 2015, Comput. Electron. Agric..

[17]  Hanno Scharr,et al.  Leaf segmentation in plant phenotyping: a collation study , 2016, Machine Vision and Applications.

[18]  Edward Jones,et al.  A survey of image processing techniques for plant extraction and segmentation in the field , 2016, Comput. Electron. Agric..

[19]  Ashok Samal,et al.  Holistic and component plant phenotyping using temporal image sequence , 2018, Plant Methods.

[20]  Anup Vibhute,et al.  Applications of Image Processing in Agriculture: A Survey , 2012 .

[21]  Johan A. K. Suykens,et al.  Least Squares Support Vector Machine Classifiers , 1999, Neural Processing Letters.

[22]  Alencar Xavier,et al.  Using unsupervised learning techniques to assess interactions among complex traits in soybeans , 2017, Euphytica.

[23]  M. Liu,et al.  A high-throughput stereo-imaging system for quantifying rape leaf traits during the seedling stage , 2017, Plant Methods.

[24]  Rohan L. Fernando,et al.  Extension of the bayesian alphabet for genomic selection , 2011, BMC Bioinformatics.

[25]  Nathan D. Miller,et al.  Computer-vision analysis of seedling responses to light and gravity. , 2007, The Plant journal : for cell and molecular biology.

[26]  Josep Peñuelas,et al.  Visible and near-infrared reflectance techniques for diagnosing plant physiological status , 1998 .

[27]  Yufeng Ge,et al.  Temporal dynamics of maize plant growth, water use, and leaf water content using automated high throughput RGB and hyperspectral imaging , 2016, Comput. Electron. Agric..

[28]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[29]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[30]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[31]  Jason R Adams,et al.  Phenotypic trait extraction of soybean plants using deep convolutional neural networks with transfer learning , 2021, Big Data and Information Analytics.

[32]  Trevor Darrell,et al.  Fully Convolutional Networks for Semantic Segmentation , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[33]  G. Wahba.  Support vector machines, reproducing kernel Hilbert spaces, and randomized GACV , 1999 .