Leaf Identification Using HOG, KNN, and Neural Networks

The main objective of this paper is to identify the leaves using the concepts of image processing. A dataset comprising 1900 images of 18 leaf species has been used to train our machine. Three major steps—image preprocessing, feature extraction (using Histogram of Oriented Gradients (HOG)) and classification—have been performed. The initial step includes grayscale conversion and represents the input image as a zero-one matrix. In the next step, 900 features have been extracted using HOG. The last step comprises classification of two supervised learning methodologies—K-nearest neighbors and backward propagation algorithm using artificial neural networks. Performance of the two methods has been compared, and artificial neural networks have proved to be a better choice with an approximate accuracy of 97%. The implementation has been carried out using MATLAB and its toolboxes.