Location

Presentation- Allen E. Paulson College of Engineering and Computing

Document Type and Release Option

Thesis Presentation (Restricted to Georgia Southern)

Faculty Mentor

Rami Haddad

Faculty Mentor Email

rhaddad@georgiasouthern.edu

Presentation Year

2021

Start Date

26-4-2021 12:00 AM

End Date

30-4-2021 12:00 AM

Keywords

Machine learning, datasets

Description

Modern machine learning problems require vast amounts of data to train and achieve optimal performance. Currently, the availability of data is highly reliant upon the previous existence of curated datasets or a strenuous collection process. This stifles research into innovative machine learning applications and often disproportionally affects smaller and less well-funded research teams. To address these concerns, a tool is proposed to help automate the image collection process. Composed of a graphical user interface and an adaptive network training scheme, the tool will expand access to large, individualized datasets for smaller and more inexperienced teams.

Academic Unit

Allen E. Paulson College of Engineering and Computing

Comments

This work is archived and distributed under the repository's standard copyright and reuse license, available here. Under this license, end-users may copy, store, and distribute this work without restriction. For questions related to additional reuse of this work, please contact the copyright owner.

Files over 10MB may be slow to open. For best results, right-click and select "Save as..."

Share

COinS
 
Apr 26th, 12:00 AM Apr 30th, 12:00 AM

Automated Image Dataset Creation via Machine Learning

Presentation- Allen E. Paulson College of Engineering and Computing

Modern machine learning problems require vast amounts of data to train and achieve optimal performance. Currently, the availability of data is highly reliant upon the previous existence of curated datasets or a strenuous collection process. This stifles research into innovative machine learning applications and often disproportionally affects smaller and less well-funded research teams. To address these concerns, a tool is proposed to help automate the image collection process. Composed of a graphical user interface and an adaptive network training scheme, the tool will expand access to large, individualized datasets for smaller and more inexperienced teams.