CLASSIFICATION OF PLANT SEEDLINGS USING DEEP LEARNING ARCHITECTURES

Abstract

Agriculture is the main source of development in the rise of human civilization and it remains a key source of many economies worldwide. It is the backbone of many underdeveloped and developing countries. Due to the increase in world population, there is an increasing demand for food and cash crops. There are a lot of changes in current climatic conditions and it is a big challenge to agriculture growth so it is an essential need to increase the plant production at lower prices. Previously established plant seedling classification methods had challenges in accurate classification for selective species of plants, we proposed a system for classification using Deep Learning in that we used Convolutional Neural Network(CNN) for classification of plant seedlings. We used VGG-16 architecture. The dataset contains 12 species of plants, 960 unique plants contains approximately 5000 images provided by Aarhus University Signal processing group collaborated with University of Southern Denmark.