Classification of Different Plant Species Using Deep Learning and Machine Learning Algorithms

In the present situation, a lot of research has been directed towards the potency of plants. These natural resources contain characteristics valuable in combat against a number of diseases. But due to lack of familiarity of these plants among human beings, an appropriate advantage of their significance cannot be drawn away. Plants also shares the certain similar characteristics of leaves like color, texture, shape or size, making them hard to classify them among others. So, to eradicate this problem, a deep learning model has been used for the purpose for classification of different plants species captured in real-time using internet of things practice. Six different plants namely Ashwagandha, Black Pepper, Garlic, Ginger, Basil, and Turmeric has been selected for this purpose. Our proposed convolutional neural network (CNN) model achieved higher performance with an accuracy of 99% when compared with other benchmark deep learning models. Also, to analyze the performance of deep learning versus machine learning models like logistic regression, decision tree, random forest, Gaussian naïve Bayes, support vector machine results were evaluated and when compared CNN outperforms against all machine learning models. The future study will be directed towards the automated plant growth estimation.