Open Access Open Access  Restricted Access Subscription or Fee Access

A Method for Facial Recognition Based On Local Features

K. Srinivasa Reddy, V. Venkata Krishna, V.Vijaya Kumar

Abstract



Recently many researchers working in the area of image processing shown tremendous interest in deriving precise face recognition methods due to its challenging nature and diverse set of applications. The present paper derived a face recognition model by taking into account the local features derived based on Local Binary Patterns (LBP). The local features of the proposed method are derived based on the combination from a subset derived from Uniform Local Binary Pattern (ULBP) and Non Uniform Local Binary Pattern (NULBP). To overcome the disadvantage of dimensionality problem, many researchers considered only ULBPs for their applications and this has made a huge number of NULBPs as miscellaneous and by which overall performance is degraded. To address this problem the present paper derived a subset called Extended-Significant Non Uniform Local Binary Pattern (E-SNULBP) from the NULBP set. Based on this E-SNULBP and its various combinations, the present paper derived a face recognition algorithm. The proposed method is implemented on Indian, American Telephone and Telegraph Company (AT and T) Olivetti Research Laboratory (ORL) and Yale databases and experimental results indicate a high facial recognition rate.

Keywords


LBP, ULBP, NULBP, miscellaneous, local features, face recognition.

Full Text:

PDF


Disclaimer/Regarding indexing issue:

We have provided the online access of all issues and papers to the indexing agencies (as given on journal web site). It’s depend on indexing agencies when, how and what manner they can index or not. Hence, we like to inform that on the basis of earlier indexing, we can’t predict the today or future indexing policy of third party (i.e. indexing agencies) as they have right to discontinue any journal at any time without prior information to the journal. So, please neither sends any question nor expects any answer from us on the behalf of third party i.e. indexing agencies.Hence, we will not issue any certificate or letter for indexing issue. Our role is just to provide the online access to them. So we do properly this and one can visit indexing agencies website to get the authentic information. Also: DOI is paid service which provided by a third party. We never mentioned that we go for this for our any journal. However, journal have no objection if author go directly for this paid DOI service.