Automatic Face Recognition System by Combining Four Individual Algorithms

Lone, Manzoor Ahmad; Zakariya, Syed Mohammad; Ali, Rashid

doi:10.1109/cicn.2011.44

Cited by 28 publications

(6 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Kar et al have developed a multialgorithmic based face recognition system, harnessing the combination of gray level 2 Journal of Electrical and Computer Engineering statistical correlation method with PCA or DCT methods, in order to intensify the performance of the systems [6]. Lone et al have developed a face recognition system based on the consolidation of scores obtained from different techniques, such as PCA, DCT, template matching using correlation, and partitioned iterative function system [7]. Imran et al have proposed fusion using popular subspace methods including PCA, LDA, locality preserving projection, and independent component analysis [8].…”

Section: Introductionmentioning

confidence: 99%

Multialgorithmic Frameworks for Human Face Recognition

Shyam

Singh

2016

Journal of Electrical and Computer Engineering

View full text Add to dashboard Cite

This paper presents a critical evaluation of multialgorithmic face recognition systems for human authentication in unconstrained environment. We propose different frameworks of multialgorithmic face recognition system combining holistic and texture methods. Our aim is to combine the uncorrelated methods of the face recognition that supplement each other and to produce a comprehensive representation of the biometric cue to achieve optimum recognition performance. The multialgorithmic frameworks are designed to combine different face recognition methods such as (i) Eigenfaces and local binary pattern (LBP), (ii) Fisherfaces and LBP, (iii) Eigenfaces and augmented local binary pattern (A-LBP), and (iv) Fisherfaces and A-LBP. The matching scores of these multialgorithmic frameworks are processed using different normalization techniques whereas their performance is evaluated using different fusion strategies. The robustness of proposed multialgorithmic frameworks of face recognition system is tested on publicly available databases, for example, AT & T (ORL) and Labeled Faces in the Wild (LFW). The experimental results show a significant improvement in recognition accuracies of the proposed frameworks of face recognition system in comparison to their individual methods. In particular, the performance of the multialgorithmic frameworks combining face recognition methods with the devised face recognition method such as A-LBP improves significantly.

show abstract

Section: Introductionmentioning

confidence: 99%

Multialgorithmic Frameworks for Human Face Recognition

Shyam

Singh

2016

Journal of Electrical and Computer Engineering

View full text Add to dashboard Cite

show abstract

“…Uma das vantagens do uso dessa abordagemé que o usuário precisa interagir diretamente com o sistema, tornando a sua invasão mais difícil. As principais modalidades que podem ser usadas como biometria são a impressão digital [1],íris [24], face [15] e recentemente os sinais cerebrais [22] e cardíacos [16].…”

Section: Introductionunclassified

Um estudo comparativo das estratégias de fusão no nível de característica para Sistemas Biométricos Multimodais baseados em face e íris

Costa¹,

Passos²,

Peres³

et al. 2015

Anais Do Simpósio Brasileiro De Sistemas De Informação (SBSI)

View full text Add to dashboard Cite

Com o avanço da tecnologia, novas abordagens para o reconhecimento automático da identidade de uma pessoa têm sido propostas e tal fato tem encorajado o emprego de Sistemas Biométricos. Essa abordagem utiliza características físicas ou comportamentais de uma pessoa para realizar a sua identificação. Os Sistemas Biométricos podem ser classificados como Unimodais ou Multimodais. Sistemas Biométricos Unimodais utilizam apenas uma modalidade biométrica para realizar o reconhecimento, ao passo que os Sistemas Biométricos Multimodais empregam duas ou mais modalidades. A construção de um Sistema Biométrico Multimodal pode ser realizada de diferentes formas, as quais são categorizadas de acordo com a sua arquitetura, nível de fusão e estratégia de fusão. O objetivo deste trabalho é investigar diferentes formas de fusão de modalidades biométricas no nível de característica, visando projetar um sistema multimodal com alto poder de reconhecimento. Neste artigo, nós utilizamos a Transformada Wavelet para extrair um conjunto de características de imagens de face e íris. Os resultados obtidos mostram que os Sistemas Biométricos Multimodais apresentam melhor desempenho que os Sistemas Biométricos Unimodais, em termos de taxa de reconhecimento calculada sobre a saída produzida pela Máquina de Vetores Suporte usada como classificador.

show abstract

“…Figure 4 shows a set of images in its original format and figure 5 shows the same images after these preprocessing steps. The training and test pairs were (12,12), (10,14), (8,16), (6,18) and (4,20), where the first coordinate represents the number of images per individual used in the training set and the second coordinate shows the number used in the test set. Figures 7 and 8, show examples of the PIE database images in their original and preprocessed formats.…”

Section: A Face Databasesmentioning

confidence: 99%

“…The recognition is achieved comparing the input face (template) with all faces (templates) stored in the reference data base and selecting the one that shows the largest matching [2,20]. The major disadvantage of this method is related to the memory requirements.…”

Section: Introductionmentioning

confidence: 99%