Document Type
Honors Thesis
Abstract
Light Field Microscopy is a 3D imaging technique that sacrifices spatial resolution to capture angular information. A neural network was developed to increase the resolution of images captured. The objective of this study is to show the application of the developed convoluted neural network towards other topics. A dataset containing chest x-ray images will be used to train, test, and analyze the neural network. The neural network will be trained by converting the images to low-resolution and using it as training data. The original high-resolution data will be used as ground truth. PSNR, SSIM and visual tests will be used to test and analyze the data. It is expected that the system will output an image that is upscaled by a factor of 2. Obtaining an upscaled image will show that the developed system can be used to upscale various images and hence can be applied towards various other fields.
Publication Date
5-1-2022
Language
English
License
This work is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 4.0 International License.
Recommended Citation
Khokhar, Murtaza Aliasgar, "APPLLICATION OF CONVOLUTIONAL NEURAL NETWORK TOWARDS IMAGE UPSCALING DEMONSTRATED VIA CHEST X-RAY DATASET" (2022). 2022 Spring Honors Capstone Projects. 51.
https://mavmatrix.uta.edu/honors_spring2022/51