An image database for benchmarking of automatic face detection and recognition algorithms

Loui, Alexander C.; Judice, Charles N.; Liu, Sheng

doi:10.1109/icip.1998.723446

Cited by 14 publications

(6 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Essas pessoas estão cadastradas num ambiente virtual de aprendizagem, ao qual esse sistema de reconhecimento facial será integrado, logo, constituindo-se como um principal motivo para a utilização dessa base de dados própria para os testes dos métodos abordados neste trabalho. No entanto, em trabalhos futuros serão utilizadas bases de imagens padronizadas [22], [23], [24], [25] para comparações de resultados, verificando a taxa de acerto em relação à literatura existente. A Figura 2 ilustra algumas faces armazenadas na base de dados utilizada.…”

Section: Experimentos E Resultadosunclassified

RedFace: um sistema de reconhecimento facial baseado em técnicas de análise de componentes principais e autofaces

Diniz

Neto

Júnior

et al. 2013

Revista Brasileira De Computação Aplicada

View full text Add to dashboard Cite

Resumo: Desenvolver um modelo computacional de reconhecimento facial não é uma tarefa trivial, eis que as faces e os estímulos visuais multidimensionais possuem características de modelagem complexa. A grande dificuldade está na modelagem de uma face que abstraia as características que as diferenciem de outras faces, já que essas apresentam poucas diferenças substanciais entre si. Embora diferentes, todas as faces possuem características como, por exemplo, uma boca, dois olhos e um nariz. No presente trabalho é proposto um sistema de reconhecimento facial desenvolvido em duas fases. Inicialmente foram utilizadas as técnicas de análise de componentes principais (PCA) e Eigenfaces (autofaces) para a extração de características da face. Na segunda fase foram aplicados os classificadores K-Nearest Neighbors (K-NN), Random Forest (Floresta Aleatória) e K-Star (K-estrela) no processo de reconhecimento da face. A validação dos algoritmos foi realizada numa base de dados contendo 1280 imagens de 64 classes distintas. Finalmente, ficou constatado que o desempenho dos algoritmos testados para sistemas de reconhecimentos de face baseado em PCA foram satisfatórios, atingindo as melhores taxas de reconhecimento, acima de 90% em todos os classificadores. Ao descobrir a melhor técnica, este será aplicado na identicação de alunos que acessam um ambiente virtual de aprendizagem. Palavras-chave:

show abstract

Section: Experimentos E Resultadosunclassified

RedFace: um sistema de reconhecimento facial baseado em técnicas de análise de componentes principais e autofaces

Diniz

Neto

Júnior

et al. 2013

Revista Brasileira De Computação Aplicada

View full text Add to dashboard Cite

show abstract

“…This method can only work on a set of images, which shows faces of similar size, pose and orientation. We chose a subset of the well known FERET database [3], which matched this criteria. The first step for learning the model graphs is to match the hand labeled model graph with all images.…”

Section: Unsupervised Collection Of Model Graphsmentioning

confidence: 99%

Emergent Graphs with PCA-features for Improved Face Recognition

Heinrichs¹,

Müller²,

Tewes³

et al. 2006

AIP Conference Proceedings

View full text Add to dashboard Cite

Built on the principles of "Learning from Nature" and "Self-organization" Elastic Bunch Graph Matching for face recognition is a defining example for Organic Computing methodology. Here, we follow these principles further to advance the method in two respects. First, the requirement for manual annotation of landmarks is reduced to one single face, from which a self-organizing selection process gradually builds up the bunches by adding the most similar face to the bunch graph and then recalculating the matching. Second, the resulting bunches are replaced by the principal components of the nodes of all persons in the database. The similarity function is restricted to a suitable subset of these components. The additional self-organizing processes lead to improved precision of landmark localization and recognition rates. Altogether, an improved data structure for face storage has emerged from the simple presentation of examples in a minimally supervised way.

show abstract

“…Recently, Kodak compiled an image database as a common test bed for direct benchmarking of face detection and recognition algorithms [94]. Their database has 300 digital photos that are captured in a variety of resolutions and face size ranges from as small as 13 Â 13 pixels to as large as 300 Â 300 pixels.…”

Section: Benchmark Test Sets For Face Detectionmentioning

confidence: 99%

Detecting faces in images: a survey

Yang

Kriegman

Ahuja

2002

IEEE Trans. Pattern Anal. Machine Intell.

2,614

117

View full text Add to dashboard Cite

ÐImages containing faces are essential to intelligent vision-based human computer interaction, and research efforts in face processing include face recognition, face tracking, pose estimation, and expression recognition. However, many reported methods assume that the faces in an image or an image sequence have been identified and localized. To build fully automated systems that analyze the information contained in face images, robust and efficient face detection algorithms are required. Given a single image, the goal of face detection is to identify all image regions which contain a face regardless of its three-dimensional position, orientation, and the lighting conditions. Such a problem is challenging because faces are nonrigid and have a high degree of variability in size, shape, color, and texture. Numerous techniques have been developed to detect faces in a single image, and the purpose of this paper is to categorize and evaluate these algorithms. We also discuss relevant issues such as data collection, evaluation metrics, and benchmarking. After analyzing these algorithms and identifying their limitations, we conclude with several promising directions for future research.

show abstract

An image database for benchmarking of automatic face detection and recognition algorithms

Cited by 14 publications

References 6 publications

RedFace: um sistema de reconhecimento facial baseado em técnicas de análise de componentes principais e autofaces

RedFace: um sistema de reconhecimento facial baseado em técnicas de análise de componentes principais e autofaces

Emergent Graphs with PCA-features for Improved Face Recognition

Detecting faces in images: a survey

Contact Info

Product

Resources

About