Soil Characterization and Classification: A Hybrid Approach of Computer Vision and Sensor Network

Abstract

This paper presents soil characterization and classification using computer vision & sensor network approach. Gravity Analog Soil Moisture Sensor with arduino-uno and image processing is considered for classification and characterization of soils. For the data sets, Amhara regions and Addis Ababa city of Ethiopia are considered for this study. In this research paper the total of 6 group of soil and each having 90 images are used. That is, form these 540 images were captured. Once the dataset is collected, pre-processing and noise filtering steps are performed to achieve the goal of the study through MATLAB, 2013. Classification and characterization is performed through BPNN (Back-propagation neural network), the neural network consists of 7 inputs feature vectors and 6 neurons in its output layer to classify soils. 89.7% accuracy is achieved when back-propagation neural network (BPNN) is used.

HybridTransferNet: soil image classification through comprehensive evaluation for crop suggestion

“…When compared to previous works in soil image classification, HybridTransferNet achieves exceptional accuracy. For instance, it surpasses the results obtained by Nguyen et al [3], Vijayakumar and Balakrishnan [24], Barman and Choudhury [25], Srunitha and Padmavathi [26], Lu et al [27], Odhiambo et al [28], Bhattacharya and Solomatine [29], Zhao et al [30], Mengistu and Alemayehu [31], Wu et al [32], Yang et al [33], Vibhute et al [34], and other studies in this field. ANN 95 Barman and Choudhury [25] SVM 91.37, 95.72 Srunitha and Padmavathi [26] SVM 95 Lu et al [27] CNN AUC=91.47 Odhiambo et al [28] SVM-poly 94.3 Bhattacharya and Solomatine [29] Decision Trees, ANN and SVM 89.34, 87 and 71.18 Zhao et al [30] ANN 88, 81 Mengistu and Alemayehu [31] Back-Propagation Neural Network (BPNN) 89.7 Wu et al [32] Multi SVM with Polynomial Kernel 79.4 and 99.2 Yang et al [33] PLS-DA and Multi SVM with Polynomial Kernel 93.33 and 96.67 Vibhute et al [34] Multi SVM with Liner kernel 71.78 Proposed Work HybridTransferNet 99.47…”

Smartphone assisting convolutional neural networks for soil texture classification in dry and wet humid conditions in West Guwahati, Assam

“…The performance of the Support Vector Machine (SVM) classifier for sand, silty, and peat soil classification was reported by Srunitha and Padmavathi (2016). Mengistu and Alemayehu (2018) from Euthopia reported a hybrid approach to soil texture analysis by using ANN with an accuracy of 89.7% for 7 different types of soil texture with the cooccurrence texture analysis. A study was reported in china for 3-class soil classification by Wu et al (2018) using SVM, ANN, and Decision Tree (DT) with an accuracy of 79.4%, 99.2%, and 66.1%, respectively.…”

The effects of multiple layers feed-forward neural network transfer function in digital based Ethiopian soil classification and moisture prediction

“…Soil characterization and classification using computer vision & sensor network approach has been studied. In their study the authors have used Gravity Analog Soil Moisture Sensor with arduino-uno and image processing as techniques to achieve the objective [8]. But, there is a gap to identify suitable learning function of neural network for better convergence and accuracy.…”

“…In the paper they have used color and shape as feature vector and as a classifier KNN, SVM and deep learning has been considered. In [32], the authors have proposed soil characterization and classification using computer vision & sensor network approach. BPNN has been used as a classifier and from the experiment they have got 89.7%.…”