• Individual Members
  • Early Career Members
  • Student Members
  • Corporate Members
  • SPIE Professional Magazine
  • Visiting Lecturers
  • Lecturer Directory
    Travel Policies
    Reimbursement
  • Women In Optics
  • BACUS Technical Group
 
Print PageEmail Page

Yufeng Zheng

Dr. Yufeng  Zheng

Assistant Professor
Alcorn State University
Department of Advanced Technologies


1000 ASU Drive
Lorman MS 39096
United States

tel: 601 877 6490
fax: 601 877 3941
E-mail: yufeng.zheng@r2image.com
Web: http://yufengzheng.r2image.com/

Area of Expertise

Image analysis, Pattern recognition, Biometrics, Computer-aided detection/diagnosis

Biography

Yufeng Zheng received his Ph.D. degree in Digital Image Processing from the Tianjin University (Tianjin, China) in 1997. He is presently with the Alcorn State University (Mississippi, USA) as an assistant professor. Dr. Zheng serves as a program director of the Computer Networking and Information Technology Program, and a director of the Pattern Recognition and Image Analysis Lab. He is the principle investigator (PI) of two federal grants and the Co-PI of several grants. So far Dr. Zheng holds two patents in glaucoma classification and face recognition, and has published three book chapters and 37 scientific papers. His research interests focus on image analysis, pattern recognition, biologically inspired image processing, biometrics, and computer-aided diagnosis. Dr. Zheng is a member of SPIE, a member of IEEE & Computer Society, and also a public speaker and technical reviewer.

Lecture Title(s)

A Novel Thermal Face Recognition Approach Based on Orientation Code
A reliable thermal face recognition system can enhance the national security applications such as prevention against terrorism, surveillance, monitoring and tracking, especially at nighttime. We proposed a novel face recognition approach utilizing thermal (long wave infrared) face images that can automatically identify a subject at both daytime and nighttime. With a properly acquired thermal image (as a probe image) in monitoring zone, the following processes will be employed: normalization, face detection, face alignment, face masking, Gabor wavelet transform, face pattern words creation, face identification by similarity measure (Hamming distance). Specifically, at each frequency band of GWT, an index number representing the strongest orientational response is selected, and then encoded in binary format to favor the Hamming distance calculation. Multiple-band orientation codes are then organized into a face pattern word (FPW) by using order statistics. If eyeglasses are present on a subject’s face, an eyeglasses mask will be automatically extracted from the probe image, and then masked with all comparing FPWs (no more transforms) stored in database. A high identification rate (98.88% with Top-1 match) has been achieved upon our preliminary face dataset (of 45 subjects) from the proposed approach regardless operating time and glasses-wearing condition.

Night Vision Enhancement with Multispectral Images by Using Advanced Fusion and Adaptive Colorization
Multispectral imagery usually presents complimentary information such as visual-band imagery and infrared imagery. There is strong evidence that the fused multispectral imagery increases the reliability of interpretation, and the colorized multispectral imagery improves observer performance and reaction times. We proposed an optimized joint approach of image fusion and colorization in order to synthesize and enhance multispectral imagery such that the resulting imagery can be automatically analyzed by computers (for target recognition) and easily interpreted by human users (for visual analysis). The proposed approach provides two sets of synthesized images, a fused image in grayscale and a colorized image in color using an advanced fusion procedure and an adaptive colorization procedure, respectively. The image fusion procedure is based on the advanced discrete wavelet (aDWT) transform. The fused image quality (IQ) can be further optimized with respect to an IQ metric by implementing an iterative aDWT procedure. On the other hand, the colorization technique renders the multispectral imagery with natural colors, which human users are use to observing in everyday life. We proposed to locally colorize the multispectral imagery by mapping the color statistics of multispectral imagery to that of daylight pictures, with which the colorized images resemble daylight pictures. This local coloring procedure also involves histogram analysis, image segmentation, and pattern recognition. The fusion and colorization approach can be performed automatically and adaptively regardless of the image contents. Experimental results with multispectral imagery taken at nighttime showed that the fused image is informative and clear, and the colored image appears realistic and natural. It is anticipated that this fusion and colorization approach with multispectral imagery will eventually lead to improved performance of remote sensing, nighttime navigation, and situational awareness.
Ready for the benefits of individual SPIE membership?
Join or Renew
Already a member? Get access to member-only content.
Sign In

Member-only Content:

These articles are available only to SPIE Members as a valuable resource.
Member-only content Icon
Icon denotes member-only content.

The Joe and Agnete Yaver Memorial Scholarship


SPIE Online Courses

At Your Pace - On Your Schedule



SPIE t-shirts, ties, and scarves are now available. Get free shipping for a limited time. Shop now.


2017 Salary Report