Feature Selection Algorithms for Plant Leaf Classification: A Survey

Choudhary, Mukesh; Hiranwal, Saroj

doi:10.1007/978-981-15-5077-5_59

Cited by 7 publications

(3 citation statements)

References 62 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A review of nature-based algorithms is presented in [3] for FS. Swarm intelligence-based, and evolutionary algorithms are the primary categories used to cast and classify nature-inspired techniques.…”

Section: Literature Reviewmentioning

confidence: 99%

A Hybrid Feature Extraction and Feature Selection Mechanism to Predict Disease in Plant Leaves

A.,

2024

JAIT

View full text Add to dashboard Cite

The health of the plants is vital to meet the demands of the food cycle. As the symptoms of disease or infection are most commonly seen in plant leaves, selecting features from plant leaves that are highly impacting plant health is crucial. Plant health is a global imperative for food security and ecological balance and must be treated as the top priority. Feature Extraction (FE) and Feature Selection (FS) are significant in Deep Learning (DL) and Machine Learning (ML) models, which are used for classification and prediction. Xception-based feature extraction and random forest classification yield accurate predictions, offering interpretability and adaptability across diverse plant diseases and datasets, benefiting agriculture. In this article, FE is performed using an Xception pre-trained model and the extracted features are sent for FS. Further, six FS methods such as ANOVA, chi-square, Sequential Forward Selection (SFS), Sequential Backward Selection (SBS), Lasso and Ridge, have been deployed and compared with machine learning algorithms such as Logistic Regression (LR), K Nearest Neighbours (KNN), Decision-Trees (DT), Random Forest (RF), Support Vector Machine (SVM), Naive-Bayes (NB) for classification. The article also proposes an Ensemble Feature Selection (EFS)-RF method, which combines feature sets from six feature selection algorithms and classifies based on majority voting. The methodology section details criteria for selecting FE and FS methods, utilizing an ensemble to maximize their respective benefits. The paper contributes to agriculture by employing a hybrid approach, integrating DL (Xception-based FE) and ML (RF-based Classification), utilizing an ensemble of FS methods to identify and assign higher weightage to features prevalent across subsets. The proposed method has outperformed other algorithms for both datasets with 98 % accuracy and 0.02 Mean Squared Error (MSE) for dataset I and 98.125 % accuracy and 0.01875 MSE for dataset II.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

A Hybrid Feature Extraction and Feature Selection Mechanism to Predict Disease in Plant Leaves

A.,

2024

JAIT

View full text Add to dashboard Cite

show abstract

“…e different physical activities were checked by the model proposed by the authors and proved that their model is better when compared to others. It will be used for leaf disease classification [40][41][42].…”

Section: Related Workmentioning

confidence: 99%

A Perspective View of Cotton Leaf Image Classification Using Machine Learning Algorithms Using WEKA

Patil¹,

Burkpalli²

2021

Advances in Human-Computer Interaction

View full text Add to dashboard Cite

Cotton is one of the major crops in India, where 23% of cotton gets exported to other countries. The cotton yield depends on crop growth, and it gets affected by diseases. In this paper, cotton disease classification is performed using different machine learning algorithms. For this research, the cotton leaf image database was used to segment the images from the natural background using modified factorization-based active contour method. First, the color and texture features are extracted from segmented images. Later, it has to be fed to the machine learning algorithms such as multilayer perceptron, support vector machine, Naïve Bayes, Random Forest, AdaBoost, and K-nearest neighbor. Four color features and eight texture features were extracted, and experimentation was done using three cases: (1) only color features, (2) only texture features, and (3) both color and texture features. The performance of classifiers was better when color features are extracted compared to texture feature extraction. The color features are enough to classify the healthy and unhealthy cotton leaf images. The performance of the classifiers was evaluated using performance parameters such as precision, recall, F-measure, and Matthews correlation coefficient. The accuracies of classifiers such as support vector machine, Naïve Bayes, Random Forest, AdaBoost, and K-nearest neighbor are 93.38%, 90.91%, 95.86%, 92.56%, and 94.21%, respectively, whereas that of the multilayer perceptron classifier is 96.69%.

show abstract

“…Hence, the classi er is used in different sectors like Bank, Healthcare, etc. Its application is in the agriculture sector that is leaf disease classi cation [39]. One of the disadvantages of this classi er is it needs more resources and computational power to build many tress so that it can combine the different trees output.…”

Section: Related Workmentioning

confidence: 99%

A Perspective View of Cotton Leaf Image Classification Using Machine Learning Algorithms Using WEKA

Patil

Barkpalli

2021

Preprint

View full text Add to dashboard Cite

Cotton is one of the major crops in India where 23% of cotton gets exported to other countries. Hence, the cotton yield depends on the crop growth, and it gets affected because of diseases. In this paper, cotton disease classification is performed using different machine learning algorithms. For this research, the cotton database was created by capturing images in the field under controlled conditions. The same database is used for segmenting the images using modified factorization-based active contour. The color and texture features are extracted from segmented images and later its fed to the machine learning algorithms like Multilayer perceptron, Support vector machine, Naïve Bayes, Random forest, Ada Boost, K nearest neighbor. The performance of the classifiers is better when color features are extracted than texture features extraction. The color features are enough to classify the healthy and unhealthy cotton leaf images. Among the different classifiers, Multilayer perceptron gives nearly 96.69% which is greater than other classifiers.

show abstract

Feature Selection Algorithms for Plant Leaf Classification: A Survey

Cited by 7 publications

References 62 publications

A Hybrid Feature Extraction and Feature Selection Mechanism to Predict Disease in Plant Leaves

A Hybrid Feature Extraction and Feature Selection Mechanism to Predict Disease in Plant Leaves

A Perspective View of Cotton Leaf Image Classification Using Machine Learning Algorithms Using WEKA

A Perspective View of Cotton Leaf Image Classification Using Machine Learning Algorithms Using WEKA

Contact Info

Product

Resources

About