Loading...
Journal Title
Readers/Advisors
Chen, Min, Easwaran, Chirakkal, Suchy, Ashley
Journal Title
Term and Year
Fall 2022
Publication Date
2022
Book Title
Publication Volume
Publication Issue
Publication Begin
Publication End
Number of pages
Collections
Files
Loading...
Curry_Thesis.pdf
Adobe PDF, 4.1 MB
Research Projects
Organizational Units
Journal Issue
Abstract
Convolutional neural networks (CNNs) have revolutionized the task of image classification, a frequently occurring computer vision problem. Progress in network architecture has been the leading factor in this advancement, with the evolution of deeper networks with fewer parameters. Alongside CNN network advancements, dataset augmentations have been implemented to expand the learnable data the network can model from. Limited dataset size is a major issue in building neural network models, particularly due to the problem of overfitting, which arises from models fitting training data too well, at the expense of capturing general trends in data, leading to large test errors. In this thesis, we augment available image data by implementing blending modes to expose the full tonal range contained in each training image. Additionally, we implement a horizontal flip transformation to create mirror versions of training images. These data augmentations are shown to reduce overfitting in CNN models. We explore different combinations of blending mode layers to maximize the validation accuracy of the network model.
Citation
DOI
Description
Accessibility Statement
If this SOAR repository item is not accessible to you (e.g. able to be used in the context of a disability), please email libraryaccessibility@newpaltz.edu