2019 - 22nd Annual Steven Galovich Memorial Student Symposium

Presentation Title

Dog Breed Identification Using Convolutional Neural Networks

Student Presenter(s) and Advisor

Xavier S. Higa, Lake Forest CollegeFollow

Department or Major

Computer Science

Computer Science, Philosophy

Location

Lillard Lobby

Abstract

Image classification is one of the classical problems of Computer Vision, and with the advent of deep convolutional neural networks, more and more fine-grained classification problems are being addressed every day. In the presented work, we try to train a deep neural network to distinguish between dog breeds based on their photographs. We also try to isolate the exact image features that uniquely identify each dog breed and gain some insight on how the classification method of a computer compares with that of a human.

Presentation Type

Poster

Start Date

4-9-2019 1:00 PM

End Date

4-9-2019 2:15 PM

Panel

Poster Session

Field of Study for Presentation

Computer Science

No downloadable materials are available for this event.

Share

COinS
 
Apr 9th, 1:00 PM Apr 9th, 2:15 PM

Dog Breed Identification Using Convolutional Neural Networks

Lillard Lobby

Image classification is one of the classical problems of Computer Vision, and with the advent of deep convolutional neural networks, more and more fine-grained classification problems are being addressed every day. In the presented work, we try to train a deep neural network to distinguish between dog breeds based on their photographs. We also try to isolate the exact image features that uniquely identify each dog breed and gain some insight on how the classification method of a computer compares with that of a human.