Wednesday 20th of September 2017
 

Efficiency of Gaussian Pyramid Compression Technique for Biometric Images


K.C.Chandra Sekaran and K.Kuppusamy

Images in their uncompressed form require large amount of storage capacity and uncompresses data needs large transmission bandwidth for the transmission. Image compression technique is used to reduce the storage requirement per image, while maintaining image quality. The proposed method investigates biometric image compression using Gaussian Pyramid Compression (GPC) in which the performance is observed down to 0.23 bits/pixel attributed to noise reduction without a significant loss of texture. Objective measures were used such as Signal to Noise Ratio (SNR), Peak Signal to Noise Ratio (PSNR), Mean Squared Error (MSE) and Bit Rate (BR) to evaluate the image quality for both gray and RGB biometric images. The comparisons of Gaussian Pyramid compression technique applied to .jpg, .bmp and .png images.

Keywords: Biometric, iris, loss-less, fingerprint, palm print, generating kernel, low-pass filter.

Download Full-Text


ABOUT THE AUTHORS

K.C.Chandra Sekaran
K.C.Chandrasekaran is working as a Associate Professor and Head, Department of Computer Sciencce, Alagappa Government Arts College, Karaikudi Sivagangai (Dt).T.N. India He has 20 years of teaching experience for both U.G. and P.G. courses . One Research paper published in National Conference organized by Presidency College, Chennai.

K.Kuppusamy
Dr.K.Kuppusamy is working as a Professor in the Department of Computer Science and Engineering, Alagappa University, Karaikukdi, Tamilnadu, India. He received his Ph.D degree in Computer Science from the dept of computer science and Engineering Alagappa University, Karaikudi, Tamilnadu in the year 2007. He has 25 years of teaching experience in the field of Computer science. He has published many papers in International & National Journals and presented in National and International conferences. His areas of research interests includes Information/Network Security, Algorithms, Neural Networks, Fault Tolerant Computing, Software Engineering and Optimization Techniques.


IJCSI Published Papers Indexed By:

 

 

 

 
About IJCSI

IJCSI is a refereed open access international journal for scientific papers dealing in all areas of computer science research...

Learn more »
Join Us
FAQs

Read the most frequently asked questions about IJCSI.

Frequently Asked Questions (FAQs) »
Get in touch

Phone: +230 911 5482
Email: info@ijcsi.org

More contact details »