Face Recognition Performance Improvement by Decomposition of Local Features using Discrete Wavelet Transforms
Journal Title: International Journal of Research in Computer and Communication Technology - Year 2013, Vol 2, Issue 11
Abstract
This paper proposes a novel method of face recognition using decomposition of local features using Discrete Wavelet Transforms (DWT). The impulse for the proposed idea is with the fact that histograms DC constituent of local Gabor binary patterns constitute low frequency components which will sparsely help in actual recognition, because information in face resides in low frequency bands and is similar to all the images and also when these histograms are concatenated, it becomes difficult to differentiate and segregate actual frequency variations which add value for accurate recognition. A high correlation exists in between these histograms. This high correlation affects the recognition accuracy, hence de-correlation is achieved with the help of DWT application in terms of detail coefficients for individual histogram bins which aids in identification of actual frequency variations and highlights the changes in between two histograms thus improving the recognition accuracy. This method employs a non-statistical procedure which avoids training step for face samples thereby avoiding generalizability problem which is caused due to statistical learning procedure. The performance modeling is carried out by varying both internal and external factors of face recognition system and improvement is shown considerably high in terms of recognition accuracy and reduction in storage space by storing train images in compressed domain.
Authors and Affiliations
Vasudha S, Neelamma K. Patil, Lokesh R. Boregowda
Keywords
Related Articles
- EP ID EP27734
- DOI -
- Views 246
- Downloads 2
A Digital Harmonic Rejection Mixer with Analog Harmonic Pre-suppression
A harmonic rejection mixer (HRM) employing analog harmonic pre-suppression and subsequent digital domain harmonic suppression is proposed and investigated. The analog harmonic pre-suppression relaxes the dynamic rang...
An Optimal and Secure Ranking Search Over out Sourced Cloud Databases
Considering top k multi keywords from the out sourced information files is still an intriguing examination issue in light of the fact that out sourced information over cloud can be scrambled for secrecy .In this pape...
Hot Spot Cell Load Balancing
Cellular network has undergone explosive growth in terms of number of subscribers in last couple of decades. Today billions of people around the world use mobile telephones, penetrating around 60 % of global populati...
Wireless real time health monitoring system built with FPGA and RF networks
In recent Days, heart disease is a major concern in the health indicator for the elderly. Cardiovascular diseases are always the leading cause of death in many countries. Due to the rapid growth of elderly population...
A Personalized Anonymization Technique Based On An Aggregate Formulation Implemented In Polynomial Time
Differential Privacy makes available a conjectural formulation for solitude that guarantees that the system basically performs the identical way despite of whether any personality is incorporated in the database. In...