Turkish Journal of Computer and Mathematics Education
Journal license

Journal

Turkish Journal of Computer and Mathematics Education


Volume
& Issue

Volume 10, Issue 1


Published
on


Pages

612-617


DOI

Article

Wavelet Transform Domain for Deep Image Compression Using High Frequency Sub-Band Prediction

Check for updates


Authors

Umang Garg* Affiliation:
Graphic Era Hill University, Dehradun Uttarakhand India 248002


Abstract

This procedure demonstrates a Two Dimensional Discrete Cosine Transform (2D-DCT) system with quantization and zigzag layout. The JPEG picture compression approach uses this process as the foundation and main channel. Utilizing the 2D- DCT property, the calculation divides the overall process into compression and decompression. Even though the data in the images remained the same, the pixel was reduced predicated on the quantization and zigzag process. Division operation is used throughout the quantization process. As a result, this procedure minimizes data loss during decompression. The theoretical research offered in this study offers some fresh perspectives on how local variation behaves when JPEG compression is applied. Additionally, it might be utilised in a few aspects of image processing and analysis, including picture enhancement, image quality evaluation, and image filtering. MATLAB is used for this project, and improved vector quantization is used. Using the compression ratio, MSE, and PSNR, we can produce compressed pictures.


Keywords

Image Compression, Two Dimensional Discrete Cosine Transform, Vector Quantization, Image Processing, Wavelet Transform


Citation

Garg, U. (2019). Wavelet transform domain for deep image compression using high frequency sub-band prediction. Turkish Journal of Computer and Mathematics Education, 10(1), 612–617. https://doi.org/10.17762/turcomat.v10i1.13556

Published by: Engineering Journals

Engineering Journals Logo