Improving the quality of images synthesized by discrete cosine transform regression-based method using principle component analysis

authors:

avatar Kian Hamedani 1 , avatar valiallah saba 2 , *

Radiation Research Center, Faculty of Paramedicine, AJA University of Medical Sciences, Tehran, Iran, Andorra
Radiation Research Center, Faculty of Paramedicine, AJA University of Medical Sciences, Tehran, Iran, Iran
Annals of Military and Health Sciences Research: Vol.12, issue 2; e63384
published online: July 24, 2014
article type: Original Article
received: March 19, 2014
accepted: May 27, 2014

how to cite: Hamedani K , saba V. Improving the quality of images synthesized by discrete cosine transform regression-based method using principle component analysis. Ann Mil Health Sci Res. 2014;12(2):e63384. 

Abstract

Materials and Methods: Two new methods, based on neural networks and principle component analysis (PCA) were used to make virtual views of an image. The results were compared with those of the DCT-based method. Two distance metrics, i.e. mean square error (MSE) and structural similarity  index measure (SSIM), were used to measure and compare image qualities. About  400 data were used to evaluate the performance of the new proposed methods.
 
 
Results: The neural networks fail to improve the quality of virtually produced images. However, principle component analysis improved the quality of the synthesized images about 3%.
 
 
Conclusion: Principle component analysis is better than both DCT-based and neural network methods for synthesizing virtual views of an    image.
 
 

Fulltext

Full text is a available in PDF.

References

  • 1.

    references is available in PDF.