An Empirical Analysis of the Performance of Convolutional Neural Network for Object Identification

This abstract provide concept of a Deep Learning algorithm, viz.; Convolutional neural networks (CNN) in image classification. The algorithm is tested on various standard datasets, like remote sensing data of aerial images (UC Merced Land Use Dataset) and scene images from SUN database. The performance of the algorithm is evaluated based on the quality metric known as Mean Squared Error (MSE) and classification accuracy. The experimental result analysis based on the quality metrics and the graphical representation proves that the algorithm (CNN) gives fairly good classification accuracy for all the tested datasets. This paper presents an empirical analysis of the performance of popular convolutional neural networks (CNNs) for identifying objects. The most popular convolution neural networks for object detection and object category classification from images are Alex Nets, GoogLeNet, and ResNet50. A variety of image data sets are available to test the performance of different types of CNN’s. The commonly found benchmark datasets for evaluating the performance of a convolutional neural network are an ImageNet dataset, and CIFAR10, CIFAR100, and MNIST image data sets. This study focuses on analyzing the performance of three popular networks: Alex Net, GoogLeNet, and ResNet50. We have taken three most popular data sets ImageNet, CIFAR10, and CIFAR100 for our study, since, testing the performance of a network on a single data set does not reveal its true capability and limitations. It must be noted that videos are not used as a training dataset; they are used as testing datasets. Our analysis shows that GoogLeNet and ResNet50 are able to recognize objects with better precision compared to Alex Net. Moreover, the performance of trained CNN’s vary substantially across different categories of objects and we, therefore, will discuss the possible reasons for this.