THE HAZARDOUS AND NORMAL PLANT CLASSIFICATION USING TENSORFLOW AND KERAS MODEL

Abstract

Abstract~ This paper proposes an efficient approach to categorize plants into hazard and normal categories using Tensor Flowand Keras models. The suggested model effectively distinguishes between different plant species based on their visual traits by utilizing deep learning techniques, specifically Convolutional Neural Networks (CNNs). The training dataset comprises a diverse range of plant photos, which enables the model to acquire complex attributes necessary for accurate categorization. During the training phase, the CNN model learns to identify pertinent patterns and characteristics from the images, which improves its accuracy in classifying data that has not yet been viewed. The model's great accuracy in identifying dangerous plants from regular ones is demonstrated by experimental results.TensorFlow and Keras work together to simplify the processes of development, training, and evaluation. This results in a plant categorization system that is accurate and effective, and can be used in a variety of industries, including forestry, agriculture, and environmental monitoring.