Click for new scientific resources and news about Corona[COVID-19]

Paper Information

Journal:   ANNALS OF MILITARY AND HEALTH SCIENCES RESEARCH   SPRING 2014 , Volume 12 , Number 2; Page(s) 80 To 85.
 
Paper: 

IMPROVING THE QUALITY OF IMAGES SYNTHESIZED BY DISCRETE COSINE TRANSFORM REGRESSION-BASED METHOD USING PRINCIPLE COMPONENT ANALYSIS

 
 
Author(s):  HAMEDANI KIAN, SABA VALIALLAH
 
* 
 
Abstract: 

Purpose: Different views of an individuals’ image may be required for proper face recognition.
Recently, discrete cosine transform (DCT) based method has been used to synthesize virtual views of an image using only one frontal image. In this work the performance of two different algorithms was examined to produce virtual views of one frontal image.
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.

 
Keyword(s): NEURALNETWORKS, FACE RECOGNITION, PRINCIPLE COMPONENT ANALYSIS, DISCRETE COSINE TRANSFORM, MEAN SQUARE ERROR, STRACTURAL SIMILLARITY INDEX MEASURMENT
 
 
References: 
  • ندارد
  •  
 
Click to Cite.
APA: Copy

HAMEDANI, K., & SABA, V. (2014). IMPROVING THE QUALITY OF IMAGES SYNTHESIZED BY DISCRETE COSINE TRANSFORM REGRESSION-BASED METHOD USING PRINCIPLE COMPONENT ANALYSIS. ANNALS OF MILITARY AND HEALTH SCIENCES RESEARCH, 12(2), 80-85. https://www.sid.ir/en/journal/ViewPaper.aspx?id=408590



Vancouver: Copy

HAMEDANI KIAN, SABA VALIALLAH. IMPROVING THE QUALITY OF IMAGES SYNTHESIZED BY DISCRETE COSINE TRANSFORM REGRESSION-BASED METHOD USING PRINCIPLE COMPONENT ANALYSIS. ANNALS OF MILITARY AND HEALTH SCIENCES RESEARCH. 2014 [cited 2021May09];12(2):80-85. Available from: https://www.sid.ir/en/journal/ViewPaper.aspx?id=408590



IEEE: Copy

HAMEDANI, K., SABA, V., 2014. IMPROVING THE QUALITY OF IMAGES SYNTHESIZED BY DISCRETE COSINE TRANSFORM REGRESSION-BASED METHOD USING PRINCIPLE COMPONENT ANALYSIS. ANNALS OF MILITARY AND HEALTH SCIENCES RESEARCH, [online] 12(2), pp.80-85. Available: https://www.sid.ir/en/journal/ViewPaper.aspx?id=408590.



 
  pdf-File
Yearly Visit 39
 
Latest on Blog
Enter SID Blog