Xiaozheng Zhang

Learn More
Mug shot photography has been used to identify criminals by the police for more than a century. However, the common scenario of face recognition using frontal and side-view mug shots as gallery remains largely uninvestigated in computerized face recognition across pose. This paper presents a novel appearance-based approach using frontal and sideface images(More)
This paper proposes a novel heterogeneous specular and diffuse (HSD) 3-D surface approximation which considers spatial variability of specular and diffuse reflections in face modelling and recognition. Traditional 3-D face modelling and recognition methods constrain human faces with either the Lambertian assumption or the homogeneity assumption, resulting(More)
INTRODUCTION Prior studies suggest that right ventricular apical (RVA) pacing has deleterious effects. Whether the right ventricular outflow tract (RVOT) is a more optimal site for permanent pacing in patients with congestive heart failure (CHF) has not been established. METHODS AND RESULTS We conducted a randomized, cross-over trial to determine whether(More)
Human-centric driver assistance systems with integrated sensing, processing and networking aim to find solutions for traffic accidents and other relevant issues. The key technology for developing such a system is the capability of automatically understanding and characterizing driver behaviors. This paper proposes a novel driving posture recognition(More)
Pacing impedance has been proposed to monitor the clinical status of patients with congestive heart failure (CHF). This study examined whether changes in right ventricular (RV) pacing impedance correlate with changes in left ventricular ejection fraction (LVEF) and New York Heart Association (NYHA) functional class during long-term follow-up in pacemaker(More)
One possible solution for poseand illuminationinvariant face recognition is to employ appearancebased approaches, which rely greatly on correct facial textures. However, existing facial texture analysis algorithms are suboptimal, because they usually neglect specular reflections and require numerous training images for virtual view synthesis. This paper(More)
One of the key remaining problems in face recognition is that of handling the variability in appearance due to changes in pose. One strategy is to synthesize virtual face views from real views. In this paper, a novel 3D face shape-modeling algorithm, Multilevel Quadratic Variation Minimization (MQVM), is proposed. Our method makes sole use of two orthogonal(More)
Tolerance to pose variations is one of the key remaining problems in face recognition. It is of great interest in airport surveillance systems using mugshot databases to screen travellers’ faces. This paper presents a novel poseinvariant face recognition approach using two orthogonal face images from mugshot databases. Virtual views under different poses(More)
3D insect models are useful to overcome viewing angle variations and self-occlusions in computer-assisted insect taxonomy for electronic field guides. The acquisition of 3D information is, however, unreliable due to the flexibility and small size of the insect bodies. This paper explores how to infer 3D insect models from a single 2D insect image, which(More)