Face Recognition Using Eigenfaces, Geometrical PCA Approximation and Neural Networks

Machidon, Alina L.; Machidon, Octavian; Ogrutan, Petre

doi:10.1109/tsp.2019.8768864

Cited by 23 publications

(20 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…gaPCA is a geometric construction-based approach for PCA approximation, which was previously validated in applications such as remote sensing image visualization [53] and face recognition [54]. Moreover, gaPCA was shown [55] to yield better performance in land classification accuracy than the standard PCA, with the most remarkable results recorded in the cases of preponderantly spectral classes.…”

Section: Description Of the Gapca Algorithmmentioning

confidence: 98%

Accelerating a Geometrical Approximated PCA Algorithm Using AVX2 and CUDA

Machidon

Ciobanu

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

Remote sensing data has known an explosive growth in the past decade. This has led to the need for efficient dimensionality reduction techniques, mathematical procedures that transform the high-dimensional data into a meaningful, reduced representation. Projection Pursuit (PP) based algorithms were shown to be efficient solutions for performing dimensionality reduction on large datasets by searching low-dimensional projections of the data where meaningful structures are exposed. However, PP faces computational difficulties in dealing with very large datasets—which are common in hyperspectral imaging, thus raising the challenge for implementing such algorithms using the latest High Performance Computing approaches. In this paper, a PP-based geometrical approximated Principal Component Analysis algorithm (gaPCA) for hyperspectral image analysis is implemented and assessed on multi-core Central Processing Units (CPUs), Graphics Processing Units (GPUs) and multi-core CPUs using Single Instruction, Multiple Data (SIMD) AVX2 (Advanced Vector eXtensions) intrinsics, which provide significant improvements in performance and energy usage over the single-core implementation. Thus, this paper presents a cross-platform and cross-language perspective, having several implementations of the gaPCA algorithm in Matlab, Python, C++ and GPU implementations based on NVIDIA Compute Unified Device Architecture (CUDA). The evaluation of the proposed solutions is performed with respect to the execution time and energy consumption. The experimental evaluation has shown not only the advantage of using CUDA programming in implementing the gaPCA algorithm on a GPU in terms of performance and energy consumption, but also significant benefits in implementing it on the multi-core CPU using AVX2 intrinsics.

show abstract

Section: Description Of the Gapca Algorithmmentioning

confidence: 98%

Accelerating a Geometrical Approximated PCA Algorithm Using AVX2 and CUDA

Machidon

Ciobanu

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…The idea of the proposed system is to identify human faces if they are recorded in the database of the system as well as categorize individuals whose images are not recorded in the database as unqualified or as strangers through the process of automatic identification [22] and identification of persons. In this phase, Eigenfaces for recognition algorithm and Geometrical Approach for Face Detection and Recognition [8] will be used.…”

Section: Phase 2: Face Recognition Algorithmmentioning

confidence: 99%

Human Face Recognition from Part of a Facial Image based on Image Stitching

Shahin¹,

Rami²,

Rayan³

et al. 2021

IJACSA

View full text Add to dashboard Cite

Most of the current techniques for face recognition require the presence of a full face of the person to be recognized, and this situation is difficult to achieve in practice, the required person may appear with a part of his face, which requires prediction of the part that did not appear. Most of the current forecasting processes are done by what is known as image interpolation, which does not give reliable results, especially if the missing part is large. In this work, we adopted the process of stitching the face by completing the missing part with the flipping of the part shown in the picture, depending on the fact that the human face is characterized by symmetry in most cases. To create a complete model, two facial recognition methods were used to prove the efficiency of the algorithm. The selected face recognition algorithms that are applied here are Eigenfaces and geometrical methods. Image stitching is the process during which distinctive photographic images are combined to make a complete scene or a high-resolution image. Several images are integrated to form a wide-angle panoramic image. The quality of the image stitching is determined by calculating the similarity among the stitched image and original images and by the presence of the seam lines through the stitched images. The Eigenfaces approach utilizes PCA calculation to reduce the feature vector dimensions. It provides an effective approach for discovering the lower-dimensional space. In addition, to enable the proposed algorithm to recognize the face, it also ensures a fast and effective way of classifying faces. The phase of feature extraction is followed by the classifier phase. Displacement classifiers using square Euclidean and City-Block distances are used. The test results demonstrate that the proposed algorithm gave a recognition rate of around 95%, to validate the proposed algorithm; it compared to the existing CNN and Multibatch estimator method.

show abstract

“…Alina L. Machidon et al, [19] have used the geometrical approximated PCA (gaPCA) to determine the eigenface rather than standard PCA to reduce the computation cost. Eigenfaces of the datasets Yale, Cambridge and LFW are computed by applying gaPCA on the face images.…”

Section: Literature Reviewmentioning

confidence: 99%

Hybrid Face recognition using Fusion of DTCWT and FDCT Features

2020

IJETER

View full text Add to dashboard Cite

The growth of automation in our daily life needs prime requirement of security. Biometric recognition or identification is one of the most important system for security and surveillance related activities compared to conventional techniques like ID cards, Personal Identification Number (PIN) and password. The biometric system security can be increased by combining multiple feature extraction algorithms rather than considering single feature extractor. The proposed work incorporates multi scale resolution techniques for extracting facial image features. The system independently incorporates Dual tree complex wavelet transform (DTCWT) technique to extract one set of features coefficients and Fast Discrete Curvelet Transform (FDCT) via wrapping to extract another set of face image features. The extracted features from both the techniques are multiplied and normalized to obtain final features. In order to classify the test feature with trained set of features Euclidean distance (ED) classifier is used. The system performance is evaluated for different face databases like FERET, L-space k, NIR and JAFFE. The values of False Acceptance Rate (FAR), False Rejection Rate (FRR), Total Success Rate (TSR) and Equal Error Rate (EER) were measured and it is found that the proposed system yields better recognition rate with minimal Equal Error Rate when compared to existing techniques.

show abstract

Face Recognition Using Eigenfaces, Geometrical PCA Approximation and Neural Networks

Cited by 23 publications

References 10 publications

Accelerating a Geometrical Approximated PCA Algorithm Using AVX2 and CUDA

Accelerating a Geometrical Approximated PCA Algorithm Using AVX2 and CUDA

Human Face Recognition from Part of a Facial Image based on Image Stitching

Hybrid Face recognition using Fusion of DTCWT and FDCT Features

Contact Info

Product

Resources

About