A High-Throughput Phenotyping Pipeline for Image Processing and Functional Growth Curve Analysis

High-throughput phenotyping system has become more and more popular in plant science research. The data analysis for such a system typically involves two steps: plant feature extraction through image processing and statistical analysis for the extracted features. The current approach is to perform those two steps on different platforms. We develop the package “implant” in R for both robust feature extraction and functional data analysis. For image processing, the “implant” package provides methods including thresholding, hidden Markov random field model, and morphological operations. For statistical analysis, this package can produce nonparametric curve fitting with its confidence region for plant growth. A functional ANOVA model to test for the treatment and genotype effects on the plant growth dynamics is also provided.

[1]  David R. Swanson,et al.  Image Harvest: an open-source platform for high-throughput plant image processing and analysis , 2016, Journal of experimental botany.

[2]  Abhiram Das,et al.  Image-Based High-Throughput Field Phenotyping of Crop Roots1[W][OPEN] , 2014, Plant Physiology.

[3]  Stephen M. Smith,et al.  Segmentation of brain MR images through a hidden Markov random field model and the expectation-maximization algorithm , 2001, IEEE Transactions on Medical Imaging.

[4]  James C. Schnable,et al.  Plant segmentation by supervised machine learning methods , 2020, The Plant Phenome Journal.

[5]  Zhiguo Cao,et al.  TasselNet: counting maize tassels in the wild via local counts regression network , 2017, Plant Methods.

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

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

[8]  Tony P. Pridmore,et al.  Deep Learning for Multi-task Plant Phenotyping , 2017, bioRxiv.

[9]  Oge Marques,et al.  Morphological Image Processing , 2011 .

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

[11]  Quan Wang,et al.  HMRF-EM-image: Implementation of the Hidden Markov Random Field Model and its Expectation-Maximization Algorithm , 2012, ArXiv.

[12]  Yumou Qiu,et al.  Functional Modeling of Plant Growth Dynamics , 2017, bioRxiv.

[13]  J. Besag.  Spatial Interaction and the Statistical Analysis of Lattice Systems , 1974 .

[14]  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..

[15]  Gilles Celeux,et al.  EM procedures using mean field-like approximations for Markov model-based image segmentation , 2003, Pattern Recognit..

[16]  J. Fox,et al.  Local Polynomial Regression , 2000 .

[17]  J. O. Ramsay,et al.  Functional Data Analysis (Springer Series in Statistics) , 1997 .

[18]  M. Tester,et al.  Image-based phenotyping for non-destructive screening of different salinity tolerance traits in rice , 2014, Rice.

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

[20]  Shubhra Aich,et al.  DeepWheat: Estimating Phenotypic Traits from Crop Images with Deep Learning , 2017, 2018 IEEE Winter Conference on Applications of Computer Vision (WACV).

[21]  Hans-Georg Müller,et al.  Functional Data Analysis , 2016 .

[22]  Zheng Xu,et al.  Simulated Plant Images Improve Maize Leaf Counting Accuracy , 2019, bioRxiv.