Zhe Guo

Northwestern Polytechnical University, Xi’an, Liaoning, China

Are you Zhe Guo?

Claim your profile

Publications (8)5.83 Total impact

  • [Show abstract] [Hide abstract]
    ABSTRACT: The increasing availability of 3D facial data offers the potential to overcome the difficulties inherent with 2D face recognition, including the sensitivity to illumination conditions and head pose variations. In spite of their rapid development, many 3D face recognition algorithms in the literature still suffer from the intrinsic complexity in representing and processing 3D facial data. In this paper, we propose the intrinsic 3D facial sparse representation (I3DFSR) algorithm for multi-pose 3D face recognition. In this algorithm, each 3D facial surface is first mapped homeomorphically onto a 2D lattice, where the value at each site is the depth of the corresponding vertex on the 3D surface. Each 2D lattice is then interpolated and converted into a 2D facial attribute image. Next, the sparse representation is applied to those attribute images. Finally, the identity of each query face can be obtained by using the corresponding sparse coefficients. The innovation of our approach lies in the strategy of converting irregular 3D facial surfaces into regular 2D attribute images such that 3D face recognition problem can be solved by using the sparse representation of those attribute images. We compare the proposed algorithm to three widely used 3D face recognition algorithms in the GavabDB database, to six state-of-the-art algorithms in the FRGC2.0 database, and to three baseline algorithms in the NPU3D database. Our results show that the proposed I3DFSR algorithm can substantially improve the accuracy and efficiency of multi-pose 3D face recognition.
    Journal of Visual Communication and Image Representation 02/2013; 24(2):117–126. · 1.20 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: The increasing availability of 3D facial data offers the potential to overcome the intrinsic difficulties faced by conventional face recognition using 2D images. Instead of extending 2D recognition algorithms for 3D purpose, this letter proposes a novel strategy for 3D face recognition from the perspective of representing each 3D facial surface with a 2D attribute image and taking the advantage of the advances in 2D face recognition. In our approach, each 3D facial surface is mapped homeomorphically onto a 2D lattice, where the value at each site is an attribute that represents the local 3D geometrical or textural properties on the surface, therefore invariant to pose changes. This lattice is then interpolated to generate a 2D attribute image. 3D face recognition can be achieved by applying the traditional 2D face recognition techniques to obtained attribute images. In this study, we chose the pose invariant local mean curvature calculated at each vertex on the 3D facial surface to construct the 2D attribute image and adopted the eigenface algorithm for attribute image recognition. We compared our approach to state-of-the-art 3D face recognition algorithms in the FRGC (Version 2.0), GavabDB and NPU3D database. Our results show that the proposed approach has improved the robustness to head pose variation and can produce more accurate 3D multi-pose face recognition.
    Pattern Recognition Letters. 01/2012; 33:530-536.
  • [Show abstract] [Hide abstract]
    ABSTRACT: It is a challenging work to achieve viewpoint independent object recognition. A new efficient method of object recognition based on 3D model is proposed in this paper. Firstly, we obtain multiple 2D projected images of a single 3D model from different directions, and then extract the normalized Fourier Descriptors of the object's edge in the projected images. According to the fact that 2D projection images within limited view range have continuity and similarity, projections can be clustered into the multiple view feature model, leading to an appropriate number of cluster classes and increases the recognition rate. Finally, the SVM classifier is used for recognition. The experiment results show the effectiveness and efficiency of method proposed.
    Proceedings of the Second Sino-foreign-interchange conference on Intelligent Science and Intelligent Data Engineering; 10/2011
  • [Show abstract] [Hide abstract]
    ABSTRACT: The paper applied the SNAKE model to segmentation of 3D real facial model: First, using physiological knowledge of the facial organs distribution to get the initial processing region; Second, using bending energy and tensile energy to compose the internal energy, using total energy of vertex's characteristic to compose external energy and using the area contained by the vertexes as the constraint, building up the equation of energy's changing; finally, doing the iterative operation to equation and get the segmentation result when the equation value is minimum. Experiment results in real 3D models show the algorithm's validity and superiority.
    Proceedings of the Second Sino-foreign-interchange conference on Intelligent Science and Intelligent Data Engineering; 10/2011
  • [Show abstract] [Hide abstract]
    ABSTRACT: In order to eliminate the effect of the facial expression and illumination condition, as well as to speed up the recognition procedure, we propose a face recognition approach based on sparse representation. First, preprocessing and segmenting the face area from three dimensional (3D) face scans, we also apply coarse to fine registration to ensure the alignment of range images; second, mapping the 3D model to range image through a kind of geometry-based resampling method; finally, employ sparse representation classification method to identify 3D face. The experiment results in actual 3D face database demonstrate the effectiveness of the proposed method.
    Computational Intelligence and Software Engineering (CiSE), 2010 International Conference on; 01/2011
  • [Show abstract] [Hide abstract]
    ABSTRACT: A 3D face recognition approach which uses principal axes registration (PAR) and three face representation features from the re-sampling depth image: Eigenfaces, Fisherfaces and Zernike moments is presented. The approach addresses the issue of 3D face registration instantly achieved by PAR. Because each facial feature has its own advantages, limitations and scope of use, different features will complement each other. Thus the fusing features can learn more expressive characterizations than a single feature. The support vector machine (SVM) is applied for classification. In this method, based on the complementarity between different features, weighted decision-level fusion makes the recognition system have certain fault tolerance. Experimental results show that the proposed approach achieves superior performance with the rank-1 recognition rate of 98.36% for GavabDB database. Keywords3D face recognition–principal axes registration (PAR)–fusion feature–weighted voting
    Frontiers of Electrical and Electronic Engineering in China 01/2011; 6(2):347-352.
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: We present a novel method for 3D face recognition, in which the 3D facial surface is first mapped into a 2D domain with specified resolution through a global optimization by constrained conformal geometric maps. The Intrinsic Shape Description Map (ISDM) is then constructed through a modeling technique capable to express geometric and appearance information of the 3D face. Hence the 3D surface matching problem can be simplified to a 2D image matching problem, which greatly reduces the computational complexity. Finally, the Intrinsic Shape Description Feature (ISDF) of ISDM and the discrimination analysis can be calculated. Experimental results implemented on GavabDB demonstrate that our proposed method significantly outperforms the existing methods with respect to pose variation.
    Acoustics Speech and Signal Processing (ICASSP), 2010 IEEE International Conference on; 04/2010 · 4.63 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: 3D information provides a significant improvement in recognition performance over 2D facial image data. However, the existing 3D approaches show limitations dealing with pose variation, e.g., 3D facial surfaces need to be aligned before the match operation. In this paper, an original framework which has the scale, rotation and expression invariance based on geometric invariant feature is proposed for automatic face recognition without pre-registration. In this study, 3D face scans are first pre-processed, including mesh cropping, holes filling, and mesh regularization; subsequently, the geometric invariant feature combined the local shape variation feature with spatial geometric feature which is invariant to scale and pose is extracted. Experimental results implemented on GavabDB and our purpose-selected database demonstrate that our proposed method significantly outperforms the state-of-the-art methods with respect to pose and facial expression variation.
    Proceedings of the Fifth International Conference on Image and Graphics, ICIG 2009, Xi'an, Shanxi, China, 20-23 September 2009; 01/2009

Publication Stats

1 Citation
5.83 Total Impact Points

Institutions

  • 2010–2013
    • Northwestern Polytechnical University
      • Shaanxi Provincial Key Laboratory of Speech and Image Information Processing
      Xi’an, Liaoning, China