Classification of Plants Using GIST and LBP Score Level Fusion

Salve, Pradip; Sardesai, Milind; Yannawar, Pravin

doi:10.1007/978-981-13-5758-9_2

Cited by 4 publications

(1 citation statement)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ali et al [13] proposed combined feature set using LBP and Bag of features for classification using SVM. Salve et al [14] proposed a multi-model plant classification system by integrating LBP and GIST features using feature-level fusion and score-level fusion techniques. Mostajer Kheirkhah and Asghari [15] proposed a model with the help of GIST texture features with PCA feature selection method.…”

Section: Preliminary Studymentioning

confidence: 99%

Plant Leaf Classification and Comparative Analysis of Combined Feature Set Using Machine Learning Techniques

Ariyapadath¹

2021

View full text Add to dashboard Cite

The main purpose of this research work is to apply machine learning and image processing techniques for plant classification efficiently. In the plant classification system, the conventional method is time-consuming and needs to apply expensive analytical instruments. The automated plant classification system helps to predict plant classes easily. The most challenging part of the automated plant classification research is to extract unique features of leaves. This paper proposes a plant classification model using an optimal feature set with combined features. The proposed model is used to extract features from leaf images and applied to image classification algorithms. After the evaluation process, it is found that GIST, Local Binary Pattern and Pyramid Histogram Oriented Gradient have better results than others in this particular application. Combined these three features extraction techniques and selected the optimal feature set through Neighbourhood Component Analysis. The optimal feature set helps classify plants with maximum accuracy in minimal time. Here performed an extensive experimental comparison of the proposed optimal feature set and other feature extraction methods using different classifiers and tested on different data sets (Swedish Leaves, Flavia, D-Leaf). The results confirm that this optimal feature set with NCA using ANN classifier leads to better classification achieved 98.99% accuracy in 353.39 seconds.

show abstract

Section: Preliminary Studymentioning

confidence: 99%