View-independent Face Recognition Research Articles

Pose invariant face recognition using biological inspired features based on ensemble of classifiers

This paper introduces a new method for view-independent face recognition by means of features inspired by the human’s visual ventral stream and ensemble of classifiers. Several sets of scale and translation invariant features are first extracted. The feature vectors are then given to a new method of ensemble of classifiers. Diversity is a crucial condition for obtaining accurate ensembles. Diversity in our method is obtained by using bootstrapped replicas of the training vectors. Different training vectors are randomly drawn from the training vectors and are connected together to form diverse training sets. Experiments were performed to validate the method on the CMU-PIE and FERET face databases. Comparison with some of the most related methods indicates that the proposed method yields better recognition rate in view independent face recognition.

Face learning and the emergence of view-independent face recognition: An event-related brain potential study

Recognizing unfamiliar faces is more difficult than familiar face recognition, and this has been attributed to qualitative differences in the processing of familiar and unfamiliar faces. Familiar faces are assumed to be represented by view-independent codes, whereas unfamiliar face recognition depends mainly on view-dependent low-level pictorial representations. We employed an electrophysiological marker of visual face recognition processes in order to track the emergence of view-independence during the learning of previously unfamiliar faces. Two face images showing either the same or two different individuals in the same or two different views were presented in rapid succession, and participants had to perform an identity-matching task. On trials where both faces showed the same view, repeating the face of the same individual triggered an N250r component at occipito-temporal electrodes, reflecting the rapid activation of visual face memory. A reliable N250r component was also observed on view-change trials. Crucially, this view-independence emerged as a result of face learning. In the first half of the experiment, N250r components were present only on view-repetition trials but were absent on view-change trials, demonstrating that matching unfamiliar faces was initially based on strictly view-dependent codes. In the second half, the N250r was triggered not only on view-repetition trials but also on view-change trials, indicating that face recognition had now become more view-independent. This transition may be due to the acquisition of abstract structural codes of individual faces during face learning, but could also reflect the formation of associative links between sets of view-specific pictorial representations of individual faces.

Global-Based Eigenspaces with Mixture of Experts for View-Independent Face Recognition using Different Representations

In this paper a model for view-independent face recognition, based on Mixture of Experts, ME is introduced. In conventional ME the problem space is divided into several subspaces for the experts, and the expertsoutputs are combined by a gating network. Basically, the way that the face space is partitioned by ME is important. In our model, experts of ME structure are not biased in any way to prefer one class of faces to another. In the other words the gating network learns a partition of input face space and selects one expert in each of these partitions. We call this method “self-directed partitioning”. In our model, different data preparation algorithm is used, LDA and PCA. The better performance of the LDA method in frontal view for face recognition due to PCA was revealed. Using this advantage of LDA and using both the LDA and the PCA in data preparation, section achieved more overall performance in face recognition due to conventional ME.

Improving mixture of experts for view-independent face recognition using teacher-directed learning

In this paper we develop a new learning method, called teacher-directed learning (TDL), for mixture of experts (ME) to perform view-independent face recognition. In the basic form of ME the problem space is automatically divided into several subspaces for the experts, and the outputs of experts are combined by a gating network. In our proposed method, the ME is directed to adapt to a particular partitioning corresponding to predetermined views. To do this, we apply a new learning method to ME, called TDL, in a way that according to the pose of the input training sample, only the weights of the corresponding experts are updated. We apply TDL to MEs, composed of MLP experts and a radial basis function gating network, with different representation schemes: global, single-view and overlapping eigenspace. We test them with previously intermediate unseen views of faces. The experimental results support our claim that directing the experts to a predetermined partitioning of the face space improves the performance of the conventional ME for view-independent face recognition. Comparison with some of the most related methods indicates that the proposed model yields excellent recognition rate in view-independent face recognition.

Teacher-directed learning in view-independent face recognition with mixture of experts using overlapping eigenspaces

A model for view-independent face recognition, based on Mixture of Experts, ME, is presented. In the basic form of ME the problem space is automatically divided into several subspaces for the experts, and the outputs of experts are combined by a gating network. In our proposed model, the ME is directed to adapt to a particular partitioning corresponding to predetermined views. To force an expert towards a particular partitioning corresponding to predetermined views, a new representation scheme, overlapping eigenspaces, is introduced, that provides each expert with an eigenspace computed from the faces in the corresponding neighboring views. Furthermore, we use teacher-directed learning, TDL, in a way that according to the pose of the input training sample, only the weights of the corresponding experts are updated. The experimental results support our claim that directing the experts to a predetermined partitioning of the face space improves the performance of the conventional ME for view-independent face recognition. Comparison with some of the most related methods indicates that the proposed model yields excellent recognition rate in view-independent face recognition.

View-independent face recognition with Mixture of Experts

A model for view-independent face recognition, based on Mixture of Experts, ME, is presented. Instead of allowing ME to partition the face space automatically, it is directed to adapt to a particular partitioning corresponding to predetermined views. Experimental results show that this model performs well in recognizing faces of intermediate unseen views. There are neurophysiological evidences that underpin the proposed model, reporting similar mechanisms of pooling the outputs of several view-specific modules to perform view-independent face recognition.

Teacher-directed learning in view-independent face recognition with mixture of experts using single-view eigenspaces

Abstract We propose a new model for view-independent face recognition by multiview approach. We use the so-called “mixture of experts”, ME, in which, the problem space is divided into several subspaces for the experts, and the outputs of experts are combined by a gating network. In our model, instead of leaving the ME to partition the face space automatically, the ME is directed to adapt to a particular partitioning corresponding to predetermined views. To force an expert towards a specific view of face, in the representation layer, we provide each expert with its own eigenspace computed from the faces in the corresponding view. Furthermore, we use teacher-directed learning, TDL, in a way that according to the pose of the input training sample, only the weights of the corresponding expert are updated. The experimental results support our claim that directing the experts to a predetermined partitioning of face space improves the performance of the conventional ME for view-independent face recognition. In particular, for 1200 images of unseen intermediate views of faces from 20 subjects, the ME with single-view eigenspaces yields the average recognition rate of 80.51% in 10 trials, which is noticeably increased to 90.29% by applying the TDL method.