Agricultural and Biological Research

Efficient multi-class image-based rosemary variety verification and classification model using deep learning

Tsega Asresa*, Melaku Bayih, Eyeuel Getachew

Artificial Intelligence (AI) has a subfield called computer vision that allows systems and computers to extract replacement data from digital photos and videos. It is used in many fields, including agriculture, health care, education, self-driving cars and daily living. In Ethiopia, rosemary is a wellknown aromatic and therapeutic plants. It is an evergreen herb that belongs to the shrub family and it is widely used specious in Ethiopia and it is classified in to three varieties such as WG rosemary I, WG rosemary II, WG rosemary III. Botanists, researchers, herbal industries, pharmacists and domain experts are facing challenges to classify appropriate varieties. And no research is conducted that identify and classify those varieties. However; there is lack of technologies’ that identify the varieties of rosemary in Ethiopia. The proposed study is employed supervised machine learning and multi class image classification. This study is conducted using convolutional neural network by employing softmax activation function as a last layer. Due to this reason we are going to implement the classification model of rosemary using multi class classification. In this study, the researchers trained five cutting-edge models: Convolutional neural network, Inception V3 and Xception. Those models were chosen after a comprehensive review of the best-performing models. The 80/20 percentage split is used to evaluate the model and classification metrics are used to compare models. The pre-trained Inception V3 model outperforms well, with training and validation accuracy of 98.8% and 97.7%, respectively.