Citation Context

...re is used to represent each face in each frame. 4.4 Feature Clustering We choose the widely known ...

Citation Context

...n with a modified form of MRH [2] for feature extraction. Details of the system components are given below. 4.1 Face Localisation For face localisation, OpenCV’s Haar Feature-based Cascade Classifier =-=[14]-=- is used to detect and localise faces in each frame. Eyes are located within each face using a Haar-based classifier. If no eyes are found, their locations are approximated based on the size of the lo...

Citation Context

...l faces through feature clustering. Conclusions and directions for future work are given in Section 6. 2 Background: Face Selection While there has been several surveys on videobased face recognition =-=[3, 4, 5, 6]-=-, face selection has not been reviewed as a component in existing face recognition systems until recently (2010) [6]. As larger video datasets are being made available including the Mobile Biometrics ...

Citation Context

...re is used to represent each face in each frame. 4.4 Feature Clustering We choose the widely known ...

Citation Context

... ...

Citation Context

...e approaches tend to integrate the information expressed by all the face images into a single model. One such image-set matching solution is to cluster similar faces by feature similarity. Lee et al. =-=[11]-=- proposed to learn a low-dimensional manifold, which is approximated by piecewise linear subspaces. To construct the representation, exemplars are first sampled from videos by finding frames with the ...

Citation Context

...pose changes in video, which are further clustered using K-means clustering. Each cluster models face appearance in nearby poses, represented by a linear subspace computed by PCA. Arandjelovic et al. =-=[12]-=- model the face appearance distribution as Gaussian Mixture Models (GMMs) on lowdimensional manifolds. In further work [13], they derived a local manifold illumination invariant, and formulated the fa...

Citation Context

...ighting changes due to variation between scenes (indoor/outdoor). In addition to the above image variations, face detection and alignment will also have great influence on the recognition performance =-=[1]-=-. Many face recognition algorithms assume the faces are well aligned and normalised, which may not be the case, especially for low quality video. Thus to address these issues, not only does the face r...

Citation Context

...to provide further robustness to varying image conditions present in ...

Citation Context

...per describes a system for video-to-video face recognition which uses an adapted form of the probabilistic Multi-Region Histogram (MRH) method originally developed for still-to-still face recognition =-=[2]-=-. We have chosen to extend it to videoto-video recognition as it has shown robustness to alignment errors as well as variations in illumination, pose and image quality. Furthermore, MRH is relatively ...

Citation Context

...r the face detection step [7]. Face confidence metrics can be based on located facial features (such as eyes and nose) within the face [8], or face classification using pre-trained binary classifiers =-=[9, 10]-=-. The number of selected faces is typically chosen in a heuristic manner, such as the number of faces or faces above a certain threshold of confidence. There are typically two main reasons for not usi...

Citation Context

...l faces through feature clustering. Conclusions and directions for future work are given in Section 6. 2 Background: Face Selection While there has been several surveys on videobased face recognition =-=[3, 4, 5, 6]-=-, face selection has not been reviewed as a component in existing face recognition systems until recently (2010) [6]. As larger video datasets are being made available including the Mobile Biometrics ...

Citation Context

...l faces through feature clustering. Conclusions and directions for future work are given in Section 6. 2 Background: Face Selection While there has been several surveys on videobased face recognition =-=[3, 4, 5, 6]-=-, face selection has not been reviewed as a component in existing face recognition systems until recently (2010) [6]. As larger video datasets are being made available including the Mobile Biometrics ...

Citation Context

... has not been reviewed as a component in existing face recognition systems until recently (2010) [6]. As larger video datasets are being made available including the Mobile Biometrics (MOBIO) dataset =-=[7]-=-, which has made face selection a more prominent topic to investigate. MOBIO has 17,480 videos and over 3 million frames — with such a large amount of information, balancing computational efficiency w...

Citation Context

...r the face detection step [7]. Face confidence metrics can be based on located facial features (such as eyes and nose) within the face [8], or face classification using pre-trained binary classifiers =-=[9, 10]-=-. The number of selected faces is typically chosen in a heuristic manner, such as the number of faces or faces above a certain threshold of confidence. There are typically two main reasons for not usi...

Citation Context

...l faces through feature clustering. Conclusions and directions for future work are given in Section 6. 2 Background: Face Selection While there has been several surveys on videobased face recognition =-=[3, 4, 5, 6]-=-, face selection has not been reviewed as a component in existing face recognition systems until recently (2010) [6]. As larger video datasets are being made available including the Mobile Biometrics ...

Citation Context

...poses, represented by a linear subspace computed by PCA. Arandjelovic et al. [12] model the face appearance distribution as Gaussian Mixture Models (GMMs) on lowdimensional manifolds. In further work =-=[13]-=-, they derived a local manifold illumination invariant, and formulated the face appearance distribution as a collection of Gaussian distributions corresponding to clusters obtained by k-means. We prop...