Evaluation of the SeedCounter, A Mobile Application for Grain Phenotyping

Grain morphometry in cereals is an important step in selecting new high-yielding plants. Manual assessment of parameters such as the number of grains per ear and grain size is laborious. One solution to this problem is image-based analysis that can be performed using a desktop PC. Furthermore, the effectiveness of analysis performed in the field can be improved through the use of mobile devices. In this paper, we propose a method for the automated evaluation of phenotypic parameters of grains using mobile devices running the Android operational system. The experimental results show that this approach is efficient and sufficiently accurate for the large-scale analysis of phenotypic characteristics in wheat grains. Evaluation of our application under six different lighting conditions and three mobile devices demonstrated that the lighting of the paper has significant influence on the accuracy of our method, unlike the smartphone type.

[1]  P. Zapotoczny.  Discrimination of wheat grain varieties using image analysis and neural networks. Part I. Single kernel texture , 2011 .

[2]  E. Shwedyk,et al.  An instrumental system for cereal grain classification using digital image analysis , 1987 .

[3]  Hanno Scharr,et al.  3D Surface Reconstruction of Plant Seeds by Volume Carving: Performance and Accuracies , 2016, Frontiers in plant science.

[4]  Wei Li,et al.  Combining discriminant analysis and neural networks for corn variety identification , 2010 .

[5]  S. Mooney,et al.  Automatic estimation of wheat grain morphometry from computed tomography data. , 2015, Functional plant biology : FPB.

[6]  Jos B. T. M. Roerdink,et al.  The Watershed Transform: Definitions, Algorithms and Parallelization Strategies , 2000, Fundam. Informaticae.

[7]  Alberto J. Palma,et al.  Using the mobile phone as Munsell soil-colour sensor: An experiment under controlled illumination conditions , 2013 .

[8]  H. Scharr,et al.  phenoSeeder - A Robot System for Automated Handling and Phenotyping of Individual Seeds1[OPEN] , 2016, Plant Physiology.

[9]  Shawn M. Kaeppler,et al.  A robust, high‐throughput method for computing maize ear, cob, and kernel attributes automatically from images , 2017, The Plant journal : for cell and molecular biology.

[10]  Simon Griffiths,et al.  A Genetic Framework for Grain Size and Shape Variation in Wheat[C][W] , 2010, Plant Cell.

[11]  Kenneth M. Dawson-Howe,et al.  A Practical Introduction to Computer Vision with Opencv , 2014 .

[12]  Alison B. Smith,et al.  GrainScan: a low cost, fast method for grain size and colour measurements , 2014, Plant Methods.

[13]  G. Venora,et al.  Image analysis of whole grains : A noninvasive method to predict semolina yield in durum wheat , 2001 .

[14]  Pablo M. Granitto,et al.  Large-scale investigation of weed seed identification by machine vision , 2005 .

[15]  M. Sorrells,et al.  Comparison of digital image analysis using elliptic Fourier descriptors and major dimensions to phenotype seed shape in hexaploid wheat (Triticum aestivum L.) , 2012, Euphytica.

[16]  Nuno M Reis,et al.  Portable smartphone quantitation of prostate specific antigen (PSA) in a fluoropolymer microfluidic device. , 2015, Biosensors & bioelectronics.

[17]  Min Huang,et al.  Review of seed quality and safety tests using optical sensing technologies , 2015 .

[18]  E. Saadaoui,et al.  Updated Methods for Seed Shape Analysis , 2016, Scientifica.

[19]  Dharmendra Saraswat,et al.  Smartphone-based hierarchical crowdsourcing for weed identification , 2015, Comput. Electron. Agric..

[20]  Jeong-Yeol Yoon,et al.  Recent approaches for optical smartphone sensing in resource-limited settings: a brief review , 2016 .

[21]  Joseph Howse.  Android Application Programming with OpenCV , 2013 .

[22]  R. Macknight,et al.  Rapid analysis of seed size in Arabidopsis for mutant and QTL discovery , 2011, Plant Methods.

[23]  Nathan D. Miller,et al.  Mapping Quantitative Trait Loci Affecting Arabidopsis thaliana Seed Morphology Features Extracted Computationally From Images , 2013, G3: Genes | Genomes | Genetics.

[24]  Meng Wang,et al.  Image-based rapid phenotyping of chickpeas seed size , 2016 .

[25]  Jeong-Yeol Yoon,et al.  Multimodal Imaging and Lighting Bias Correction for Improved μPAD-based Water Quality Monitoring via Smartphones , 2016, Scientific Reports.

[26]  Wiesnerová Dana,et al.  Computer image analysis of seed shape and seed color for flax cultivar description , 2008 .

[27]  Hamid Reza Pourreza,et al.  Identification of nine Iranian wheat seed varieties by textural analysis with image processing , 2012 .

[28]  Smýkalová Iva,et al.  Phenotypic evaluation of flax seeds by image analysis , 2013 .

[29]  W. John Kress,et al.  Leafsnap: A Computer Vision System for Automatic Plant Species Identification , 2012, ECCV.

[30]  Noel D.G. White,et al.  Evaluation of the effect of moisture content on cereal grains by digital image analysis , 2007 .

[31]  M. Yano,et al.  SmartGrain: High-Throughput Phenotyping Software for Measuring Seed Shape through Image Analysis1[C][W][OA] , 2012, Plant Physiology.

[32]  S. Pethybridge,et al.  Leaf Doctor: A New Portable Application for Quantifying Plant Disease Severity. , 2015, Plant disease.

[33]  Lingfeng Duan,et al.  A novel machine-vision-based facility for the automatic evaluation of yield-related traits in rice , 2011, Plant Methods.

[34]  Zhiguo Cao,et al.  Crop segmentation from images by morphology modeling in the CIE L*a*b* color space , 2013 .