Multi-view face detection in open environments is a challenging task, due to the wide variations in illumination, face appearances and occlusion. In this paper, a robust method for multi-view face detection in open environments, using a combination of Gabor features and neural networks, is presented. Firstly, the effect of changing the Gabor filter parameters (orientation, frequency, standard d...

We introduce “wave atoms” as a variant of 2D wavelet packets obeying the parabolic scaling wavelength ∼ (diameter). We prove that warped oscillatory functions, a toy model for texture, have a significantly sparser expansion in wave atoms than in other fixed standard representations like wavelets, Gabor atoms, or curvelets. We propose a novel algorithm for a tight frame of wave atoms with redund...

For a given class F of uniform frames of fixed redundancy we define a Grassmannian frame as one that minimizes the maximal correlation |〈fk, fl〉| among all frames {fk}k∈I ∈ F . We first analyze finite-dimensional Grassmannian frames. Using links to packings in Grassmannian spaces and antipodal spherical codes we derive bounds on the minimal achievable correlation for Grassmannian frames. These ...

Inspired by biological vision systems, the over-complete local features with huge cardinality are increasingly used for face recognition during the last decades. Accordingly, feature selection has become more and more important and plays a critical role for face data description and recognition. In this paper, we propose a trainable feature selection algorithm based on the regularized frame for...

Face Recognition (FR) has a wide range of applications, such as face-based video indexing, human-computer interaction, and surveillance system. The recognition rate can reach more than 90% with the frontal face, while dealing with faces are oriented or rotated, the accuracy just achieves 40% or 50%. Hence, an algorithm is proposed in this paper to deal with the problem. The face pose is first d...

In this paper, we propose a method to track multiple deformable objects in sequences (with a static camera) in and beyond the visible spectrum by combining Gabor filtering and clustering. The idea is to sample moving areas between two frames by randomly positioning samples over high magnitude area of a motion likelihood function. These points are then clustered to obtain one class for each movi...

Consider a continuous function g ∈ L2(R) that is supported on [−1, 1] and generates a Gabor frame with translation parameter 1 and modulation parameter 0 < b < 2N 2N+1 for some N ∈ N. Under an extra condition on the zeroset of the window g we show that there exists a continuous dual window supported on [−N, N]. We also show that this result is optimal: indeed, if b > 2N 2N+1 then a dual window ...

We demonstrate a system capable of tracking, in real world image sequences, landmarks such as eyes, mouth, or chin on a face. In the standard version, knowledge previously collected about faces is used for finding the landmarks in the first frame. In a second version, the system is able to track the face without any prior knowledge about faces and is thus applicable to other object classes. By ...

We generalize the windowed Fourier transform to the variable-windowed Fourier transform. This generalization brings the Gabor transform and the wavelet transform under the same framework. Using frame theory we characterize frames and orthonormal bases for the variable windowed Fourier series (VWFS). These characterizations are formulated explicitly in terms of window functions. Therefore they c...