A computer-assisted soil texture analysis using digitally scanned images

•Particle-size distribution using scanned soil digital images.•LSSVM regression model can accomplish soil contents.•Computer vision recognition of soil textural classification.•The new method provides immediate analysis as opposed to the 2-day standard analysis.•The new analytical method is environm...

Full description

Saved in:
Bibliographic Details
Published in:Computers and electronics in agriculture 2020-07, Vol.174, p.105435, Article 105435
Main Authors: de Oliveira Morais, Pedro Augusto, de Souza, Diego Mendes, Madari, Beata Emoke, de Oliveira, Anselmo Elcana
Format: Article
Language:English
Subjects:
Algorithms
Clay
Digital image processing
Digital imaging
Environmental impact
Least squares method
LSSVM
Multivariate analysis
Multivariate image analysis
Particle size
Pipette method
Regression analysis
Sand
Soil analysis
Soil properties
Soils
Support vector machines
Texture
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:•Particle-size distribution using scanned soil digital images.•LSSVM regression model can accomplish soil contents.•Computer vision recognition of soil textural classification.•The new method provides immediate analysis as opposed to the 2-day standard analysis.•The new analytical method is environment-friendly. A computer-assisted soil texture analysis is presented using digitally scanned soil images of 177 soil samples collected from different regions of Brazil. Soil digital images were correlated to texture results determined by the standard pipette method using three multivariate methods: successive projections algorithm combined with multivariate linear regression (SPA-MLR), partial least-squares regression (PLSR), and least-squares support vector machine regression (LSSVMR). Sand and clay particle size were better estimated using LSSVMR presenting correlations above 90%. Following soil sample particle size content estimates, soil texture classes were also estimated achieving 90.6% accuracy. The proposed method using digital images is fast, cheap and has low environmental impact when compared to the standard method.
ISSN:0168-1699
1872-7107
DOI:10.1016/j.compag.2020.105435