John Y. A. Wang

Alumni of BCS Perception Group

Where I am

You can always email me at: jyawang@alum.mit.edu

I'm currently a Senior Computer Vision Software Engineer with the IP-Core Research Department of ScanSoft Inc., Palo Alto, CA.

Current Address:

3400 Hillview Ave., PAHV-305

Palo Alto, CA 94304

(650) 813-7451 (o)

(650) 857-6792 (f)

jyawang@adoc.xerox.com

I was previously with Hewlett-Packard Laboratories in Palo Alto, CA.

Research interests

Video coding, image representation, motion estimation, image/video content-based storage and retrieval

PhD Thesis Advisor

Edward H. Adelson

Education

PhD, Electrical Engineering and Computer Sciences
Massachusetts Institute of Technology, 1997

SB/SM, Electrical Engineering and Computer Sciences
Massachusetts Institute of Technology, 1987

Experience

ScanSoft, Inc. A Xerox Compnay, Palo Alto, CA
Research and develpment in optical character recognition, page layout analysis, and image enhancement.

Hewlett-Packard Laboratories, Palo Alto, CA
Research and develpment in image and video analysis and management, face detection and recognition, and image resolution enhancement.

Massachusettes Institute of Technology, Cambridge, MA
Research in image representation
Department of Brain and Cognitive Sciences - BCS Perception Group
The MIT Media Laboratory - Vision and Modeling Group
Doctoral candidate in Department of Electrical Engineering and Computer Science

Oracle Corporation, Redwood City, CA
Database Development Engineer and Consultant

Hughes Aircraft Company, El Segundo, CA
Custom Circuit Researcher/Designer

Texas Instruments, Dallas, TX
Custom Circuit Researcher/Designer

Doctoral Research

We are currently developing a video coding scheme that uses mid-level vision concepts to achieve a decomposition that can achieve higher data compression and can be applied to a wider domain of image material. Our representation consists of a set of overlapping layers where each layer contains an intensity map that defines the additive values of each pixel, along with an alpha map that serves as a mask indicating the transparency. These layers are ordered in depth and they occlude each other in accord with the rules of compositing, in a manner similar to traditional ``cel'' animation.

This layered representation is more flexible than standard image coding schemes and can capture semantic properties of natural image sequences. These properties allow us to efficiently characterize, annotate, and manipulate video data.

Publications

J. Y. A Wang and E. H. Adelson. Representing Moving Images with Layers. The IEEE Transactions on Image Processing Special Issue: Image Sequence Compression, 3(5):625-638, September 1994.

J. Y. A. Wang and E. H. Adelson. Spatio-Temporal Segmentation of Video Data. Proceedings of SPIE on Image and Video Processing II, Vol. 2182, pp. 120-131, San Jose, February 1994.

J. Y. A. Wang and E. H. Adelson. Applying Mid-level Vision Techniques for Video Data Compression and Manipulation. Proceedings of SPIE on Digital Video Compression on Personal Computers: Algorithms and Technologies, Vol. 2187, pp. 116-127, San Jose, February 1994.

J. Y. A. Wang and E. H. Adelson. Layered Representation for Motion Analysis. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition 1993, pp. 361-366, New York, June 1993.

J. Y. A. Wang and E. H. Adelson. Layered Representation for Image Sequence Coding. Proceedings of the 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing, Vol. 5, pp. 221-224, Minneapolis, April 1993.

E. H. Adelson and J. Y. A. Wang. Single Lens Stereo with Plenoptic Camera. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 14, No. 2, pp. 99-106, February 1992.

E. H. Adelson and J. Y. A. Wang. A Stereoscopic Camera Employing a Single Main Lens. Proceedings IEEE Computer Society Conference on Computer Vision and Pattern Recognition 1991, Hawaii, June 1991, pp. 619-624.

A. N. Karanicoloas, K. K. O, J. Y. Wang, H. S. Lee, R. L. Reif. A High Frequency Fully Differential BiCMOS Operational Amplifier. Proceedings of the IEEE 1990 Custom Intergrated Circuits Conference, Boston, May 1990.

Resume

HTML Format - long version

MS-Word Format - short version
(please use "save link as" and use .doc file extension)

Patent

Wang and Adelson, System for encoding image data intyo multiple layers representing regions of coherent motion and associated motion parameters. US Patent #05557684 (1996). [Abstract], [Patent].

Six U.S. Patents filed jointly with Hewlett-Packard Laboratories, Palo Alto, CA. (1997-1998)

Photos

Perceptual Science Group Home Page

Last modified: Fri Feb 19 17:06:54 1999