Classifiers Comparison for Convolutional Neural Networks (CNNs) in Image Classification

Abstract

This paper presents a comparison between five different classifiers (Multi-class Logistic Regression (MLR), Support Vector Machine (SVM), k-Nearest Neighbor (kNN), Random Forest (RF) and Gaussian Naive Bayes (GNB)) to be used in a Convolutional Neural Network (CNN) in order to perform images classification. For our experiments we have used a dataset composed of images of objects belonging to 256 widely varied categories called Caltech 256.