A Survey of 2D Face Recognition Techniques

Chihaoui, Mejda; Elkefi, Akram; Bellil, Wajdi; Amar, Chokri Ben

doi:10.3390/computers5040021

Cited by 86 publications

(51 citation statements)

References 103 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Is it segmentation of face parts or maybe some filter transformation? (Chihaoui et al, 2016) Figuring this out analytically is not feasible. The data generating process is often very complex and contains many latent factors of variations, which makes the separation and identification of those factors hard.…”

Section: Manualmentioning

confidence: 99%

A review of modularization techniques in artificial neural networks

Amer

Maul

2019

Artif Intell Rev

View full text Add to dashboard Cite

Artificial neural networks (ANNs) have achieved significant success in tackling classical and modern machine learning problems. As learning problems grow in scale and complexity, and expand into multi-disciplinary territory, a more modular approach for scaling ANNs will be needed. Modular neural networks (MNNs) are neural networks that embody the concepts and principles of modularity. MNNs adopt a large number of different techniques for achieving modularization. Previous surveys of modularization techniques are relatively scarce in their systematic analysis of MNNs, focusing mostly on empirical comparisons and lacking an extensive taxonomical framework. In this review, we aim to establish a solid taxonomy that captures the essential properties and relationships of the different variants of MNNs. Based on an investigation of the different levels at which modularization techniques act, we attempt to provide a universal and systematic framework for theorists studying MNNs, also trying along the way to emphasise the strengths and weaknesses of different modularization approaches in order to highlight good practices for neural network practitioners.

show abstract

Section: Manualmentioning

confidence: 99%

A review of modularization techniques in artificial neural networks

Amer

Maul

2019

Artif Intell Rev

View full text Add to dashboard Cite

show abstract

“…With reference to the weighting scheme used in (11), the discrimination function is defined by the following expression:…”

Section: Fig 10: Graphical Representation Of the Sprtmentioning

confidence: 99%

Incorporating Metadata in Multibiometric Score-Level Fusion: an Optimized Architecture

2019

IJITEE

View full text Add to dashboard Cite

 This manuscript presents a review on multibiometrics using ancillary information, in addition to the main biometric data. The proposed method involves taking non-biometric information into account in the biometric recognition process to improve system performance. This ancillary information can come from the user (the skin color), the sensor (the camera flash, etc.) or the operating environment (the ambient noise). Moreover, the paper presents an extension of the adapted sequential fusion framework through a complete description of the method used for the score-level fusion architecture presented at the IEEE BioSmart 2019 Proceedings. An optimized score-level fusion architecture is proposed. An introduction of new concepts (namely "biochemical features" and "multi origin biometrics") is also made. The first part of the paper highlights the various biometric systems developed up to now, their architecture and characteristics. Then, the manuscript discussed about multibiometrics through its advantages, its diversity and the different levels of fusion. An attention was paid to the score-level fusion before addressing the consideration of ancillary information (or metadata) in multibiometrics. Dealing with the affective computing, the influence of emotion on the performance of biometric systems is explored. Finally, a typology of biometric adaptation is discussed.As an application, the proposed methodology will implement a multibiometric system using the face, contactless fingerprint and skin color. A single sensor will be used (a camera) with two shots while the skin color will be extracted automatically from the facial image.

show abstract

“…To obtain the features clusters, a set of 93 images of faces (Figure 4(a)) was analysed. After reviewing several well-known databases [71], we selected the Chicago Face Database (CFD) [72]. This database contains high-resolution standardized images of real faces of Asian, Black, Latino, and White males and females with several expressions (including neutral).…”

Section: Alleles Of the Facialmentioning

confidence: 99%

Evolutionary Computation for Modelling Social Traits in Realistic Looking Synthetic Faces

et al. 2018

View full text Add to dashboard Cite

Human faces play a central role in our lives. Thanks to our behavioural capacity to perceive faces, how a face looks in a painting, a movie, or an advertisement can dramatically influence what we feel about them and what emotions are elicited. Facial information is processed by our brain in such a way that we immediately make judgements like attractiveness or masculinity or interpret personality traits or moods of other people. Due to the importance of appearance-driven judgements of faces, this has become a major focus not only for psychological research, but for neuroscientists, artists, engineers, and software developers. New technologies are now able to create realistic looking synthetic faces that are used in arts, online activities, advertisement, or movies. However, there is not a method to generate virtual faces that convey the desired sensations to the observers. In this work, we present a genetic algorithm based procedure to create realistic faces combining facial features in the adequate relative positions. A model of how observers will perceive a face based on its features’ appearances and relative positions was developed and used as the fitness function of the algorithm. The model is able to predict 15 facial social traits related to aesthetic, moods, and personality. The proposed procedure was validated comparing its results with the opinion of human observers. This procedure is useful not only for creating characters with artistic purposes, but also for online activities, advertising, surgery, or criminology.

show abstract

A Survey of 2D Face Recognition Techniques

Cited by 86 publications

References 103 publications

A review of modularization techniques in artificial neural networks

A review of modularization techniques in artificial neural networks

Incorporating Metadata in Multibiometric Score-Level Fusion: an Optimized Architecture

Evolutionary Computation for Modelling Social Traits in Realistic Looking Synthetic Faces

Contact Info

Product

Resources

About