NORMA eResearch @NCI Library

Comparing Convolution Neural Network For Single Object Vs Multiple Object Classification

Raghava, Rahul (2019) Comparing Convolution Neural Network For Single Object Vs Multiple Object Classification. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
Preview
PDF (Master of Science)
Download (4MB) | Preview

Abstract

Convolution Neural Network of huge network size can classify several objects in the image ranging up to 1000 objects. The accuracy of the network might be high, but the accuracy of each individual object varies. The accuracy of a few objects would be less than the average accuracy of the network. But few applications used for image classification would just require to classify single objects in an image. If the application requires a single object to classify, the network could be trained for it. The research paper compares the accuracy of the convolution neural network for a single object and multi object, which could provide better understanding of the network to select a single object or multiple objects for training the network.

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
Q Science > QA Mathematics > Computer software
T Technology > T Technology (General) > Information Technology > Computer software
Divisions: School of Computing > Master of Science in Cloud Computing
Depositing User: Dan English
Date Deposited: 03 Jun 2020 17:38
Last Modified: 03 Jun 2020 17:38
URI: https://norma.ncirl.ie/id/eprint/4237

Actions (login required)

View Item View Item