Hybridization of Enhanced Orthogonal and Uncorrelated Locality Preserving Projection for Dimensionality Reduction: An HEOULPP Strategy
Ummadi Sathish Kumar, Edara Sreenivasa Reddy · International journal of intelligent engineering and systems · 2020
A recent development of a linear dimension reduction (DR) algorithm that is often used in face recognition and other applications has been used to preserve the Locality preserving projection algorithm (LPP).However, in LPP the projection matrix is not orthogonal, so rendering and other apps are not easily reconstructed.Hybridization of Enhanced Orthogonal and Uncorrelated Locality Preserving Projection (HEOULPP) attempts to discover the subspace that best distinguishes distinct face classes by maximizing the gap and reducing the uncertainty within class.In the design of a similarity matrix, HEOULPP algorithm assumes both local data and label data, and needs statistically improved and orthogonal output-base vectors, in order to enhance the OLPP life grade extraction performance.We propose HEOULPP to minimize the locality in an orthogonal projection matrix and to maximize the globality.This investigation is conducted using three datasets, such as YALE face dataset, ORL face dataset, and AR face dataset.Our proposed HEOULPP techniques achieves higher facial recognition rate under three conditions such as occlusion by 70.6%, noise by 69.1% and original by 76.2% than the existing techniques.In addition, dimensionality also reduced in proposed HEOULPP method comparing with traditional methods, including PCA, LPP, OLPP, ULPP and FOLPP.Experimental findings indicated a stronger depiction of data and much greater accuracy in the suggested HEOULPP method.