A Robust High Performance Face Recognition using Decorrelation of Local Features by Discrete Cosine Transforms

Journal Title: INTERNATIONAL JOURNAL OF COMPUTERS & TECHNOLOGY - Year 2013, Vol 11, Issue 7

Abstract

This paper proposes a novel method of face recognition using de-correlation of local features using Discrete Cosine Transforms (DCT). 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 DCT application 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 Honeywell

Keywords

Related Articles

Efficient Data Forwarding Mechanism in Backbone Networks by Employing MPLS Technology

Multiprotocol Label Switching (MPLS) is a relatively new WAN technology that is attracting the networking professionals around the globe. Many ISPs have already deployed it in their network. Yet, some other ISPs are in t...

Multi-Layered Dynamic Encryption Security Scheme for Cloud Data Storage

This journal article discusses our Dynamic Encryption Key Security Scheme (DEKSS) and the purpose it serves in providing a new security architecture for protecting databases used in technology stacks involving Mobile and...

Certification des coopératives et stratification sociale dans les communautés cacaoyères en Côte d’Ivoire

La certification des coopératives a été envisagée à partir de la campagne 2004/2005 pour faire face à la menace des pays exportateurs de ne plus payer le cacao ivoirien du fait du travail d’enfants dans les exploitations...

Imprementation of Sochastic Searching for Complex Processes Identification

This paper presents implementation of stochastic searching method for complex technological process identification. As the first step of control systems design is identification of a process mathematcal model. The author...

An Improved Min-Min Task Scheduling Algorithm with Grid Utilization and Minimized Makespan

Grid computing is hardware and software infrastructure which offers a economical, distributable, coordinated and credible access to strong computational abilities [1]. For optimal use of the abilities of large distribute...

Download PDF file
  • EP ID EP650362
  • DOI 10.24297/ijct.v11i7.3492
  • Views 77
  • Downloads 0

How To Cite

Vasudha Honeywell (2013). A Robust High Performance Face Recognition using Decorrelation of Local Features by Discrete Cosine Transforms. INTERNATIONAL JOURNAL OF COMPUTERS & TECHNOLOGY, 11(7), 2801-2818. https://europub.co.uk./articles/-A-650362