IMAGE CLASSIFICATION USING MACHINE LEARNING TECHNIQUES

Plant species classification using leaf samples is a challenging and important problem to solve. This paper introduces a new dataset of sixteen samples each of one-hundred plant species; and describes a method designed to work in conditions of small training set size and possibly incomplete extraction of features. This motivates a separate processing of three feature types: shape, texture, and margin; combined using a probabilistic framework. The texture and margin features use histogram accumulation, while a normalized description of contour is used for the shape. In this paper we are using different Machine Learning algorithms to classify images based on different parameters to identify and compare the accuracy. Python supported open source modules are used here and loading the sample datasets collecting from internet and implement different neural network approachesto preprocessthe data and analysesthe output results.