DEEP LEARNING BASED PLANT SPECIES CLASSIFICATION USING DIGITAL MORPHOMETRIC MANAGEMENT

Abstract

The number of plant species is extremely huge all over the world. Hence, it is impossible to identify and classify all the species. Plant species may be similar to each other, taking a long time to differentiate them. Hence, there is a need to develop an automated system. Deep learning has been widely employed for classification and recognition tasks in the biological fields. An automated plant species identification system could help botanists. Deep learning is used for feature extraction as it provides deeper information of images. Plant species identification includes preprocessing, feature extraction, and classification. Here we used many algorithms to analyze the image. The paper aims at understanding preprocessing, extracting the leaf features using contours, and classifying them using deep-learning techniques, namely CNN (AlexNet). It presents the leaves of various plant species from which the vein characteristics are extracted and presented to detect and classify various kinds of plant species and other artificial intelligence techniques used to perform pattern recognition. Here the classifier achieved the best performance of 82% for accuracy.