Integration of Convolutional Autoencoder with Support Vector Machine for Almond Varieties Classification

Abstract

This research aims to optimize almond variety classification by integrating Convolutional Autoencoder (CAE) as a feature extraction method and Support Vector Machine (SVM) for classification. The research process includes data collection from available datasets, preprocessing, and splitting data for training and testing. Features from almond images are extracted using CAE, which are then used in the SVM model for classification. Model evaluation shows a classification accuracy of 97% on the test data, a significant increase compared to the 48% accuracy of conventional SVM. The CAE-SVM approach offers more compact and informative feature representations, effectively improving almond variety recognition. This study highlights the potential of combining CAE and SVM advantages to enhance plant image analysis and encourages further advancements in machine learning applications in agriculture.