A Comparative Analysis of Machine Learning Algorithms for Detection of Organic and Nonorganic Cotton Diseases

Table 11

Comparative study of various segmentation and classification techniques.

S. no	Name of the author and year	Segmentation	Classification	Remarks	Dataset
2	Prashar et al. [48]	KNN	(i) Support vector machine	Accuracy 96%; Precision = 91%	Self-database
3	Usha Kumari et al. [45]	K-means clustering	Artificial neural networks	Precision = 90%; Recall = 80%; Accuracy 92.5%	Self-database
5	Bhimte and Thool [44]	PCA	Support vector machine	Accuracy 98.46%	130 images
6	Masud et al. [55]	Image segmentation using Gaussian kernel function	—	Segmentation Accuracy = 63.99%	Self-database
7	Mehta et al. [36]	Decision tree	Random forest	RR = 95.30%; Sensitivity = 82.12%	Self-database
12	Sarangdhar and Pawar [9]	Machine learning using regression IoT	—	Accuracy 83.26%; Precision = 81%; Recall = 79.1%	900 images of cotton leaves; 629 are trained; 271 are for testing
13	Vijaya Kishor et al. [51]	SVM tool classification	—	Accuracy 96%	Postgre SQL
14	Parikh et al. [32]	K-means clustering	SVM	Accuracy 82.5%	150 images40 images of 1024 × 1024 pixels
17	Pujari et al. [53]	K-means clustering	ANN; PNN; SVM	Accuracy of ANN 84.11%; PNN 86.48%; SVM 85%	Self-database
21	Schuster et al. [34]	K-means clustering	Artificial neural network	Accuracy 88%; F-score = 87.91%	Self-database