Design and implementation of an efficient rose leaf disease detection and classification using convolutional neural network

Abstract

Roses are the most planted flowers in world and are grown to make profit and regarded as symbol of love. Diseases are harmful to plants' health, which in turn has adverse impact on the life cycle and quality of flowers. In order to ensure quality and minimum losses to cultivate, it is essential to develop an effective prevention mechanism. This paper has introduced modelling of rose plant disease classification systems based on concept of pre-trained learning mechanism of convolutional neural network. The proposed computational classification model uses multi-level pre-processing scheme as an auxiliary tool for feature learning and accurate disease identification. The modelling of proposed model is carried out on basis of analytical research methodology with prime objective of gaining higher performance. The study outcome shows better performance with an accuracy rate of 97.3% in disease classification. The scope of proposed work is justified based on performance analysis and comparative assessment.