Restricted accessResearch articleFirst published online 2021-01-04
Exploring simple K-means clustering algorithm for automating segregation of colors in leaf of Axonopus compressus: Towards maintenance of an urban landscape
Images of green infrastructure (gardens, green corridor, green roofs and grasslands) large area can be captured and processed to provide spatial and temporal variation in colours of plant leaves. This may indicate average variation in plant growth over large urban landscape (community gardens, green corridor etc). Towards this direction, this short technical note explores development of a simple automated machine learning program that can accurately segregate colors from plant leaves. In this newly developed program, a machine learning algorithm has been modified and adapted to give the proportion of different colors present in a leaf. Python script is developed for an image processing. For validation, experiments are conducted in green house to grow Axonopus compressus. Script first extracts different RGB (Red Green and Blue) colors present in the leaf using the K-means clustering algorithm. Appropriate centroids required for the clusters of leaf colors are formed by the K-means algorithm. The new program provides saves computation time and gives output in form of different colors proportion as a CSV (Comma-Separated Values) file. This study is the first step towards the demonstration of using automated programs for the segregation of colors from the leaf in order to access the growth of the plant in an urban landscape.
GadiV.K., GargA., RattanB., RajP., GauravS., SreedeepS., SahooL., BerrettaC. and PengL., Growth dynamics of deciduous species during their life period: A case study of urban green space in India, Urban Forestry & Urban Greening43 (2019), 126380.
2.
LiuX.P., YangC., HanF.Q., FangZ.Y., YangL.M., ZhuangM., LvH., LiuY., LiZ. and ZhangY.Y., Genetics and fine mapping of a yellow-green leaf gene (ygl-1) in cabbage (Brassica oleracea var. capitata L.), Molecular Breeding36(6) (2016), 82. https://doi.org/10.1007/s11032-016-0509-4
3.
ZhangL., WangL., WangJ., SongZ., RehmanT.U., BureetesT., MaD., ChenZ., NeenoS. and JinJ., Leaf Scanner: A portable and low-cost multispectral corn leaf scanning device for precise phenotyping, Computers and Electronics in Agriculture167 (2019), 105069. https://doi.org/10.1016/j.compag.2019.105069
4.
ShengZ.H., WeiX.J., ShaoG.N., JianS.O.N.G., JuL.U.O., HuP.S., TangS.Q. and ChenL.Y., Genetic analysis and molecular mapping of novel white striped leaf mutant gene in rice, Rice Science20(5) (2013), 336–342. https://doi.org/10.1016/S1672-6308(13)60142-0
5.
KerkechM., HafianeA. and CanalsR., Deep leaning approach with colorimetric spaces and vegetation indices for vine diseases detection in UAV images, Computers and Electronics in Agriculture155 (2018), 237–243. https://doi.org/10.1016/j.compag.2018.10.006
6.
ChemuraA., MutangaO. and DubeT., Separability of coffee leaf rust infection levels with machine learning methods at Sentinel-2 MSI spectral resolutions, Precision Agriculture18(5) (2017), 859–881. https://doi.org/10.1007/s11119-016-9495-0
7.
FeilhauerH., SchmidT., FaudeU., Sánchez-CarrilloS. and CirujanoS., Are remotely sensed traits suitable for ecological analysis? A case study of long-term drought effects on leaf mass per area of wetland vegetation, Ecological Indicators88 (2018), 232–240. https://doi.org/10.1016/j.ecolind.2018.01.012
8.
GuanZ., Abd-ElrahmanA., FanZ., WhitakerV.M. and WilkinsonB., Modeling strawberry biomass and leaf area using object-based analysis of high-resolution images, ISPRS Journal of Photogrammetry and Remote Sensing163 (2020), 171–186. https://doi.org/10.1016/j.isprsjprs.2020.02.021
9.
SunojS., IgathinathaneC., SaliendraN., HendricksonJ. and ArcherD., Color calibration of digital images for agriculture and other applications, ISPRS Journal of Photogrammetry and Remote Sensing146 (2018), 221–234. https://doi.org/10.1016/j.isprsjprs.2018.09.015
10.
HonradoJ.L.E., SolpicoD.B., FavilaC.M., TongsonE., TangonanG.L. and LibatiqueN.J., UAV imaging with low-cost multispectral imaging system for precision agriculture applications, In 2017 IEEE Global Humanitarian Technology Conference (GHTC) (2017), 1–7. IEEE. https://doi.org/10.1109/GHTC.2017.8239328
11.
AnushaM., HariniE., HegdeS.S. and KumarV.R., Segregation of Mulberry Leaves using Image Processing, International Journal of Research in Engineering, Science and Management2(5) (2019), 1051–1055.
12.
MohantyS.P., HughesD.P. and SalathéM., Using deep learning for image-based plant disease detection, Frontiers in Plant Science7 (2016), 1419. https://doi.org/10.3389/fpls.2016.01419
13.
MaL., GuL., LiB., MaY. and WangJ., An improved K-means algorithm based on mapreduce and grid, International Journal of Grid & Distributed Computing8(1) (2015), 189–200. http://dx.doi.org/10.14257/ijgdc.2015.8.1.18
14.
JainA.K., MurtyM.N. and FlynnP.J., Data clustering: a review, ACM computing surveys (CSUR)31(3) (1999), 264–323. http://dx.doi.org/10.1145/331499.331504
15.
ShenV.R., ChiouG.J., LinY.N. and JhanJ.Y., Novel Text Recognition Based on Modified K-Clustering and Hidden Markov Models, Wireless Personal Communications111(3) (2020), 1453–1474. https://doi.org/10.1007/s11277-019-06926-6
16.
HuangZ.Y., LinS., LongL.L., CaoJ.Y., LuoF., QinW.C., SunD. and GregersenH., Predicting the morbidity of chronic obstructive pulmonary disease based on multiple locally weighted linear regression model with K-means clustering, International Journal of Medical Informatics (2020), 104141. https://doi.org/10.1016/j.ijmedinf.2020.104141
17.
AytaçE., Unsupervised learning approach in defining the similarity of catchments: Hydrological response unit based k-means clustering, a demonstration on Western Black Sea Region of Turkey, International Soil and Water Conservation Research. 2020. In press. https://doi.org/10.1016/j.iswcr.2020.05.002
18.
GovenderP. and SivakumarV., Application of k-means and hierarchical clustering techniques for analysis of air pollution: A review (1980–2019), Atmospheric Pollution Research11(1) (2020), 40–56. https://doi.org/10.1016/j.apr.2019.09.009
19.
SunD. and LiddleM.J., Field occurrence, recovery, and simulated trampling resistance and recovery of two grasses, Biol Conserv57 (1991), 187–203. https://doi.org/10.1016/0006-3207(91)90138-Y
20.
XinP., LiB., ZhangH. and HuJ., Optimization and control of the light environment for greenhouse crop production, Sci Rep9 (2019), 8650. https://doi.org/10.1038/s41598-019-44980-z
21.
GadiV.K., BordoloiS., GargA., SahooL., BerrettaC. and SekharanS., Effect of shoot parameters on cracking in vegetated soil, Environmental Geotechnics5(2) (2017), 123–130. https://doi.org/10.1680/jenge.17.00013
22.
BordoloiS., HussainR., GadiV.K., BoraH., SahooL., KarangatR., GargA. and SreedeepS., Monitoring soil cracking and plant parameters for a mixed grass species, Géotechnique Letters8(1) (2018a), 49–55. https://doi.org/10.1680/jgele.17.00145
23.
BordoloiS., GadiV.K., HussainR., SahooL., GargA., Sreedeep...S. and PoulsenT.G., Influence of Eichhornia crassipes fibre on water retention and cracking of vegetated soils, Géotechnique Letters8(2) (2018b), 130–137. https://doi.org/10.1680/jgele.17.00181
24.
GanesanS.P., BordoloiS., NiJ., SizmurT., GargA. and SekharanS., Exploring implication of variation in biochar production on geotechnical properties of soil, Biomass Conversion and Biorefinery (2020), 1–11. https://doi.org/10.1007/s13399-020-00847-2
25.
LiuC., TangC.S., ShiB. and SuoW.B., Automatic quantification of crack patterns by image processing, Computers & Geosciences57 (2013), 77–80. https://doi.org/10.1016/j.cageo.2013.04.008.
26.
AnangshaA., GadiV.K., BordoloiS., KothapalliS.K., SreedeepS., GuoxiongM. and GargA., A new autonomous program customized for computing surface cracks in an unsaturated soil in a 1-D column, Journal of Testing and Evaluation47(5) (2019), 3822–3835. https://doi.org/10.1520/JTE20180609.
27.
KhandareV., HuangH., GargA., LinP. and LiuJ., Novel PythonVideo Processing Programfor Identifying and Quantification of Soil Cracks in Real Time, Signal, Image and Video Processing. (2020).
28.
CaoZ., WangY. and LiD., Quantification of prior knowledge in geotechnical site characterization, Engineering Geology203 (2016), 107–116. https://doi.org/10.1016/j.enggeo.2015.08.018.
29.
CaoZ.J., ZhengS., LiD.Q. and PhoonK.K., Bayesian identification of soil stratigraphy based on soil behaviour type index, Canadian Geotechnical Journal56(4) (2019), 570–586. https://doi.org/10.1139/cgj-2017-0714.
30.
LiX., ShenH., LiH. and ZhangL., Patch matching-based multitemporal group sparse representation for the missing information reconstruction of remote-sensing images, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing9(8) (2016), 3629–3641. DOI: 10.1109/JSTARS.2016.2533547
31.
LiX., FengR., GuanX., ShenH. and ZhangL., Remote Sensing Image Mosaicking: Achievements and Challenges, in IEEE Geoscience and Remote Sensing Magazine 7(4) (2019), 8–22, doi: 10.1109/MGRS.2019.2921780
32.
OngS.H., YeoN.C., LeeK.H., VenkateshY.V. and CaoD.M., Segmentation of color images using a two-stage self-organizing network, Image and Vision Computing20(4) (2002), 279–289. https://doi.org/10.1016/S0262-8856(02)00021-5
33.
ChenZ.S., ChinK.S., LiY.L. and YangY., Proportional hesitant fuzzy linguistic term set for multiple criteria group decision making, Information Sciences357 (2016), 61–87. https://doi.org/10.1016/j.ins.2016.04.006
34.
ChenZ.S., YangY., WangX.J., ChinK.S. and TsuiK.L., Fostering linguistic decision-making under uncertainty: A proportional interval type-2 hesitant fuzzy TOPSIS approach based on Hamacher aggregation operators and andness optimization models, Information Sciences500 (2019a), 229–258. https://doi.org/10.1016/j.ins.2019.05.074
35.
ChenZ.S., LiM., KongW.T. and ChinK.S., Evaluation and selection of hazmat transportation alternatives: a PHFLTS-and TOPSIS-integrated multi-perspective approach, International Journal of Environmental Research and Public Health16(21) (2019b), 4116. https://doi.org/10.3390/ijerph16214116
36.
ChenZ.S., YuC., ChinK.S. and MartínezL., An enhanced ordered weighted averaging operators generation algorithm with applications for multicriteria decision making, Applied Mathematical Modelling71 (2019c), 467–490. https://doi.org/10.1016/j.apm.2019.02.042
