The study of plant phenotype using segmentation techniques is one the leading research area in the field of agricultural technology. Plant phenotype is a technical term which is used to describe the observable characteristics of the plant like width, height, biomass, plant, leaf shape and so on. It is required in order to study about the physical characteristics of the plant like finding the area, height, width, structure of the plant and skeleton generation of the plant root etc. It is used in the field of agricultural technology to carry out various types of research. This paper explores the use of different segmentation methods in order to get efficient segmented images for the plant`s shoot and root systems. The segmentation methods used are threshold segmentation, edge detection, and followed by contour segmentation on PlantCV platform. The proposed work partitions the segmentation process in four steps, where the output of each step is given as input to the next step. We use the thresholding method as a first step in plant image segmentation process to remove the background and noise in the image. This step is followed by edge detection method to remove the unwanted regions and to detect false edges in a segmented plant image. Next, the contour segmentation is used to identify the complete structure of the plant. Then from the output image obtained, features are extracted in JSON format and the segmented images acquired are stored in an output folder.

Segmentation, Phenotype, Sobel operator, PlantCV platform, Shoot module, Root module, Contour Segmentation, Edge Detection, threshold Segmentation, Gaussian Blur, Median Blur, Region of Interest(ROI)

[1] H. Al-Hiary, S. Bani-Ahmad, M. Reyalat, M. Braik and Z. ALRahamneh,“ Fast and Accurate Detection and Classification of Plant Diseases“, International Journal of Computer Applications , Vol. 17,No.1, pp. 0975 – 8887, 2011.
[2] Andrade-Sanchez P., Gore M.A., Heun J.T., Thorp K.R., Carmo-Silva A.E., French A.N., Salvucci M.E.,White J.W. “Development and evaluation of a field-based high-throughput phenotyping platform”.Funct. Plant Biol. 41: 68-79; 2014.
[3] V. Sivakumar and V. Murugesh for “Segmentation of a digital image using Thresholding Technique on a Noisy Image”, ISBN No.978-1-4799-3834-6/14/$31.00©2014 IEEE, 2014.
[4] Sheetal Israni and Swapnil Jain, “Edge Detection of License Plate Using Sobel Operator”, International Conference on Electrical, Electronics, and Optimization Techniques (ICEEOT) – 2016.
[5] Fari Muhammad Abubakar, “A Study of Region- Based and Contour based Image Segmentation”, Signal & Image Processing: An International Journal (SIPIJ) Vol.3, No.6, December 2012.
[6] S. Inderpal and K. Dinesh, “A Review on Different Image Segmentation Techniques”, IJAR, Vol.. 4, April, 2014.
[7] S. Saleh, N. V. Kalyankar and S. Khamitkar, “Image segmentation by using edge detection”, (IJCSE) International Journal on Computer Science and Engineering Vol. 02, No. 03, 2010.
[8] K. H. Knuth, “Optimal data-based binning for histograms,” Ar Xiv Physics e-prints, May 2006.
[9] N.Valliammal and Dr.S.N.Geethalakshmi, “Plant Leaf Segmentation Using Non Linear K means Clustering“, IJCSI International Journal of Computer Science, Vol 9, Issues9, Issue ISSN (Online): 1694-0814, 2016.
[10] Chupin M., Hasboun D., Poupon F., Baillet S., Garnero L. Segmentation of the amygdalo – hippocampal complex by competitive region growing [MRI analysis], IEEE International Symposium, 2002.