Qin Shi

Beijing University of Technology, Peping, Beijing, China

Are you Qin Shi?

Claim your profile

Publications (11)0 Total impact


  • No preview · Article · Jan 2010 · Beijing Gongye Daxue Xuebao / Journal of Beijing University of Technology
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: A novel nonlinear face recognition method named GPPface is proposed in this paper. GPPface is based on nonlinear dimensionality reduction algorithm, geodesic preserving projection (GPP). As face images are regarded to be embedded in a nonlinear space, GPP is presented to nonlinearly map high-dimensional face images to low-dimensional feature space. GPP overcomes the weaknesses of traditional linear and nonlinear dimensionality reduction algorithms, well preserves the intrinsic structure of the manifold and can fast and efficiently map new sample point to feature space. To recover space structure of face images and tackle small sample size problem, 3D morphable model is developed to derive multiple images of a person from a single image. Experimental results on ORL and PIE face databases show that our method makes impressive performance improvement compared with conventional face recognition methods
    Preview · Conference Paper · Aug 2006
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: A novel model matching method based on genetic algorithm is presented in this paper for 3D face reconstruction. Having constructed the morphable model, genetic algorithm is proposed to tackle model matching problem. Multi-lights illumination model is developed to fit for more complex conditions. New model matching method based on genetic algorithm is independent from initial values and more robust than stochastic gradient descent method. Crossover and mutation probability are regulated during optimization process to improve precision and convergence speed of the algorithm. Multi-lights illumination model improves the stability of 3D face reconstruction and ability to evaluate illumination conditions of input facial images. Experimental results show the proposed method has good performance on 3D face reconstruction
    Preview · Conference Paper · Jan 2006
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: A novel 3D facial animation model is proposed in this paper to generate realistic facial animation sequence. The 3D facial animation model is constructed based on morphable model and compatible with MPEG-4. Uniform mesh resampling method is put forward to align prototypic 3D faces and facial animation principle defined in MPEG-4 is adopted to drive the 3D facial animation model. The animation model can automatically reconstruct realistic 3D face of specific person given a single image and be driven by FAP parameters to generate 3D facial animation sequence automatically. Experimental results show the 3D facial animation model proposed in this paper can effectively generate high realistic facial animation sequence automatically.
    Preview · Conference Paper · Sep 2005
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, Fisherface is extended for face recognition from one example image per person. Fisherface is one of the most successful face recognition methods. However, Fisherface requires several training images for each face, so it cannot be applied to face recognition applications where only one example image per person is available for training. To tackle this problem, Fisherface method is extended by utilizing 3D morphable model to derive multiple images of a face from one single image. Experimental results on ORL face database and UMIST face database show that face recognition method proposed in this paper makes impressive performance improvement compared with conventional eigenface methods.
    Preview · Conference Paper · Sep 2005
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Fisherface is enhanced in this paper for face recognition from one example image per person. Fisherface requires several training images for each face and can hardly be applied to applications where only one example image per person is available for training. We enhance Fisherface by utilizing morphable model to derive multiple images of a face from one single image. Region filling and hidden-surface removal method are used to generate virtual example images. Experimental results on ORL and UMIST face database show that our method makes impressive performance improvement compared with conventional Eigenface methods.
    Preview · Article · Sep 2005
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: An improved adaptive principal component extraction algorithm is proposed in this present study to overcome the high algorithm complexity and high computing complexity that exists in the present algorithms. The computing complexity is decreased by improving the update equation of feed-forward network weight value. Parallel algorithm of the improved adaptive principal component extraction is also presented. The experimental results on ORL face database show the improved adaptive principal component extraction algorithm is efficient in the facial feature extraction.
    Preview · Article · Jun 2005 · Journal of Computational Information Systems
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: This present study, proposes a new 3D face correspondence method. A uniform mesh re-sampling algorithm is combined with mesh simplification algorithm to make correspondence between vertices of prototypical 3D faces. Uniform mesh re-sampling algorithm is developed to obtain the same topology between 3D faces with different structures. A global error metrics is proposed and mesh simplification is implemented on 3D faces with same topologies simultaneously. The new method overcomes the limitation of conventional uniform mesh re-sampling and optical flow algorithm, decreases the vertices, and triangles that need to represent 3D face while preserving correspondence between vertices of the prototypes. The experimental results show the new method gives good performance on computing 3D face correspondence.
    Preview · Article · Jun 2005 · Journal of Computational Information Systems
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: In this present study, a face recognition method is proposed based on improved adaptive principal component extraction algorithm with Morphable model. Improved adaptive principal component extraction algorithm is proposed to compress high-dimensional facial image data. A 3D Morphable model is adopted to derive multiple images of a face from a single facial image. The experimental results on ORL and UMIST face database show the proposed method gives impressive performance and improvement compared with the conventional Eigenface methods.
    Preview · Article · Jun 2005
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: A novel model matching method based on improved genetic algorithm is presented in this paper to improve efficiency of matching process for 3D face synthesis. New method is independent from initial values and more robust than stochastic gradient descent method. Improved genetic algorithm has strong global searching ability. Crossover and mutation probability are regulated during optimization process to improve precision and convergence speed of the algorithm. Experimental results show our new model matching method has good performance on 3D face synthesis.
    Preview · Article · Jan 2005
  • [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we use local linear embedding and linear discriminant analysis for face recognition. Local linear embedding method is used to nonlinearly map high-dimensional face images to low-dimensional feature space. To recover space structure of face images, we use 3D morphable model to derive multiple images of a person from one single image. Experimental results on ORL and UMIST face database show that our method make impressive performance improvement compared with conventional Fisherface method.
    No preview · Chapter · Jan 2005