Zhigang Deng

Publications (63) View all

• Article: Live Speech Driven Head-and-Eye Motion Generators.

  Binh H Le, Xiaohan Ma, Zhigang Deng
  [show abstract] [hide abstract]
  ABSTRACT: This paper describes a fully automated framework to generate realistic head motion, eye gaze, and eyelid motion simultaneously based on live (or recorded) speech input. Its central idea is to learn separate yet inter-related statistical models for each component (head motion, gaze, or eyelid motion) from a pre-recorded facial motion dataset: i) Gaussian Mixture Models and gradient descent optimization algorithm are employed to generate head motion from speech features; ii) Nonlinear Dynamic Canonical Correlation Analysis model is used to synthesize eye gaze from head motion and speech features, and iii) non-negative linear regression is used to model voluntary eye lid motion and log-normal distribution is used to describe involuntary eye blinks. Several user studies are conducted to evaluate the effectiveness of the proposed speech-driven head and eye motion generator using the well-established paired comparison methodology. Our evaluation results clearly show that this approach can significantly outperform the state-of-the-ar t head and eye motion generation algorithms. In addition, a novel mocap+video hybrid data acquisition technique is introduced to record high-fidelity head movement, eye gaze, and eyelid motion simultaneously.
  IEEE transactions on visualization and computer graphics. 02/2012;
• Article: A Statistical Quality Model for Data-Driven Speech Animation.

  Xiaohan Ma, Zhigang Deng
  [show abstract] [hide abstract]
  ABSTRACT: In recent years, data-driven speech animation approaches have achieved significant successes in terms of animation quality. However, how to automatically evaluate the realism of novel synthesized speech animations has been an important yet unsolved research problem. In this paper we propose a novel statistical model (called SAQP) to automatically predict the quality of on-the-fly synthesized speech animations generated by various data-driven techniques. Its essential idea is to construct a phoneme-based, Speech Animation Trajectory Fitting (SATF) metric to describe speech animation synthesis errors and then build a statistical regression model to learn the association between the obtained SATF metric and the objective speech animation synthesis quality. Through delicately designed user studies, we evaluate the effectiveness and robustness of the proposed SAQP model. To the best of our knowledge, this work is the first-of-its-kind, quantitative quality model for data-driven speech animation. We believe it is the important first step to remove a critical technical barrier for applying data-driven speech animation techniques to numerous online or interactive talking avatar applications.
  IEEE transactions on visualization and computer graphics. 02/2012;
• Article: A Surface-Based 3-D Dendritic Spine Detection Approach From Confocal Microscopy Images.

  Qing Li, Zhigang Deng
  IEEE Transactions on Image Processing. 01/2012; 21:1223-1230.
• Source

  Available from: uh.edu

  Conference Proceeding: Extracting geometric features of aortic valve annulus motion from dynamic MRI for guiding interventions

  N.V. Navkar, E. Yeniaras, D.J. Shah, N.V. Tsekos, Zhigang Deng
  [show abstract] [hide abstract]
  ABSTRACT: Transcatheter aortic valve implant (TAVI) has emerged as a prominent approach for treating aortic stenosis. Success of such implants depends upon the accurate assessment of the geometric features such as the diameter, center and orientation of the aortic valve annulus (AVA). In this paper, we present a method for extracting these geometric features from magnetic resonance images (MRI). The method is based on finding an optimal fit for a circular ring mimicking AVA in the aortic root. Moreover, the presented approach provides dynamic tracking of the AVA in CINE MR images. This approach can be used for preoperative planning of prosthetic valve implantation, as well as for the emerging MRI guided manual, or with robot-assisted, annuloplasty.
  Biomedical Imaging: From Nano to Macro, 2011 IEEE International Symposium on; 05/2011
• Article: A Global Spatial Similarity Optimization Scheme to Track Large Numbers of Dendritic Spines in Time-Lapse Confocal Microscopy.

  Qing Li, Zhigang Deng, Yong Zhang, Xiaobo Zhou, U. Valentin Nagerl, Stephen T. C. Wong
  IEEE Trans. Med. Imaging. 01/2011; 30:632-641.