An Intelligent Dog Breed Recognition System Using Deep Learning

Abstract

Image processing has been getting great attention recently in the field of machine learning and deep learning. This technique can be used to process an image in such a way that the computer understands the features of the image and classifies it. Our study focuses on building an efficient CNN model to predict the breed of the dog using its image, giving the best accuracy possible with the least amount of computing resources involved. This CNN model is deployed on cloud service, Google App Engine which identifies certain characteristics or features in an image such as the paw, nose, stout, and ears of a dog, employing a dataset containing 10222 images of different dog breeds or classes of dogs and opening a wide scope for future developments.