Luc Vincent
Over 15 years experience in applied image processing R&D and software
development. Internationally recognized expert in image and document
analysis. Equally effective in startups, large business groups,
commercial research labs, or as a consultant. Strong leadership
skills, with experience including management of technical teams,
coordination of complex programs across business groups, and
contributions to corporate development and business strategy at the
senior staff level.
Ph.D. in Morphological Image Processing,
École Nationale Supérieure des Mines de Paris, France, 1990
Masters (``Diplôme d'Études Avancées'') in Computer
Science, Paris XI University, France, 1987
B.S. (``Diplôme d'Ingénieur''), Majoring in Mathematics and
Computer Science, Ecole Polytechnique, France, 1986
Google, Inc. |
2004-present |
Uber Tech Lead
Leader of several large geo-related projects, including Street
View, unveiled in May 2007. Responsible for various engineering
aspects of Google Book Search. Head of Google OCR-related
initiatives. Founder and manager of several new engineering efforts.
LizardTech, Inc. |
2000-2004 |
LizardTech is an imaging software company focusing on the compression
and efficient delivery of complex content over computer networks.
In 2000, the company acquired the DjVu (pronounced
``Déjà-Vu'') document compression and delivery technology from
AT&T Labs. DjVu is a file format, a set of advanced document image
compression algorithms, and a technology platform for distributing color
documents, whether scanned or electronically produced. LizardTech is
commercializing and further developing this outstanding technology,
targeting it to become the de facto standard for document
delivery over the Internet.
Vice President, Document Imaging (2003-2004)
Responsible for all aspects of the LizardTech document imaging product
line, including, marketing, strategy, product management, alliances,
etc.
- Overhaul document imaging strategy following Company's
acquisition by Celartem Technology.
- Instrumental in revamping Lizardtech's marketing activities in
the area of document imaging: web site, newsletters, interviews, press
releases, collateral, webinars, trade shows, etc.
- Start aggressive product development effort to support new
strategy with key features and product improvements. Deeply involved
in the design and implementation of new watermarking and document
rights management (DRM) capabilities.
- Negotiate alliances with a large number of scanner vendors,
imaging companies, content management providers and various technology
partners, in a bid to enhance the company's distribution channels and
to increase end-users exposure to the DjVu technology.
Chief Scientist, Document Imaging (2001-2003)
Share time evenly between technical activities, product development
and business development, all centered around DjVu.
- Chief company-wide technical resource on DjVu and more
broadly, on document imaging.
- Deeply involved in the design and implementation of new products
for conversion of electronic documents to DjVu, specifically a
Virtual Printer Driver for Windows, and a command-line
PDF-to-DjVu converter.
- Worked closely with product management team on all aspects of
document imaging product line: feature sets, user interface, supported
platforms, competitive analysis, schedule, pricing, licensing,
documentation, packaging, distribution, etc.
- Relentlessly evangelized DjVu via conference
presentations, publications, and the creation of compelling DjVu
content.
- Identified, negotiated and assisted in closing strategic deals
involving the DjVu technology. Instrumental in closing at least
four major deals.
Director of Applied Research, Document Imaging (2000-2001)
Led DjVu Applied Research team while remaining an active
individual contributor. Along with senior staff, helped refine company
strategy in the area of document imaging and played proactive role in
business development.
- Championed and undertook major R&D initiatives, in particular:
new set of algorithms, programs and services enabling the effective
creation of DjVu from electronic sources; development of set of
document image preprocessing algorithms such as automatic cropping,
deskewing, speckle removal, etc.
- Through publications, conference presentations, and invited
lectures, helped promote DjVu and identify strategic partners for
LizardTech. Increasingly involved in business development.
- Main point of contact for AT&T research team in their frequent
interactions with LizardTech.
- Strong advocate for LizardTech's continued involvement in
open-source activities.
Xerox Palo Alto Research Center (PARC), Advanced
Systems Development Laboratory |
1999-2000 |
The Adanced Systems Development Lab (ASD) is the newest lab at
PARC. Its mission is twofold: help Xerox realize the value of PARC
research through effective technology transfer; bring business group
needs and perspective back to PARC.
Manager, Imaging Components & Services
Led a team of 8 researchers and developers. Supported ASD's mission in
the area of imaging through development of rock-solid sofware
components. Collaborated with other PARC teams and coordinated efforts
with Xerox business groups.
- Supervised development of a DataGlyph encoding/decoding
toolkit and its deployment in a range of Xerox solutions. DataGlyphs
are a compelling alternative to 2D barcodes, providing higher data
density and improved reliability in an aesthetically pleasing
manner. Improved accuracy of decoding degraded DataGlyph images by two
orders of magnitude.
- Managed development and productization of a technology known
internally as DigiPaper. Core of technology is a document
representation method based on multi-layer decomposition/segmentation
and token-based compression. It provides ``visually lossless''
representation, with compression ratios far in excess of what standard
methods can achieve, and very fast decompression/rendering. Released
DigiPaper 1.0 in May 2000, for use in web-based legal document
repository.
- Evangelized value of DigiPaper to Xerox business groups. Led
efforts to promote technology as the foundation for Xerox next
generation products in the area of scanning, document repositories,
and mid-range color printing.
- Coordinated image processing development activities across
several geographically distributed R&D teams.
- Helped identify new business development opportunities and
negotiated new strategic alliances for Xerox.
- Promoted adhesion to set of strict guidelines for improving the
software process (Capability Maturity Model).
ScanSoft is a Xerox subsidiary with a complex history: founded in the
80s by Ray Kurzweil to make reading machines for the blind, it was
acquired by Xerox a few years later, progressively shifted its focus
to scanning software, and eventually went public in early 1999 through
a reverse merger with Visioneer. From 1990 to 1999, it was known as
Xerox Imaging Systems (XIS), and for three of these years, it
was folded into a large Xerox group called the Software Solutions Division (SSD).
Director, Advanced Development, ScanSoft (Palo Alto, CA, 1997-1999)
- Led focused engineering team responsible for advanced image
processing development, in support for ScanSoft's entire product
line. In particular, team developed large parts of the core software
used by Pagis Pro, a scanning software package that received a
number of prestigious awards and became the best selling scanning
suite on the market.
- Managed development of software components for segmentation,
adaptive thresholding, and smart compression of scanned document
pages; automatic cropping, noise cleaning, deskewing, and enhancement
of document images; image indexing and retrieval; superresolution and
image ``stitching'', enabling the production of high quality images
from inexpensive digital cameras.
- Promoted and supervised the writing of half a dozen invention
proposals and patent applications.
- Put in place a number of methods for assuring that developed code
adheres to the highest standards and meets product team needs (version
control, requirement discussions, automatic builds and regression
tests on various platforms, automatic documentation extraction, etc.).
- Kept close ties with Xerox PARC and other research organizations
to guarantee steady flow of new ideas to ScanSoft.
- Participated in business strategy discussions at ScanSoft's senior
staff level.
Director, Software Development, Xerox Software Solutions
Division (Palo Alto, CA, 1996-1997)
- Managed Image Processing Core Technology Group, a team
delivering cutting-edge document image analysis software to a diverse
base of internal customers (software and hardware product
teams). Supervised releases of about a million lines of C code, on
five different platforms (Windows NT, Windows 3.1, Macintosh, SunOS,
Solaris).
- Responsible for handling SSD's relationship with Xerox research
groups, including PARC and the European Research Center (XRCE).
Managed a $4M budget for contracting specific technology pieces with
these research groups. Facilitated technology transfer from Xerox
research into SSD, and coordinated efforts to supply PARC and XRCE
with specific research directions.
Manager, Image Processing and Analysis, Xerox Imaging
Systems (Peabody, MA, 1995-1996)
- Led team of three engineers (including 2 contractors). Provided
technical guidance and led development of document image analysis
algorithms, primarily aimed at TextBridge OCR product.
- Initiated a number of government proposals, and was
awarded a $0.5M contract by National Security Agency. Project
involved the development of new methods for automatically benchmarking
page segmentation algorithms, a topic of great interest to Xerox, but
that could not have been considered without external funding. Served
as principal investigator for this contract for over two years:
responsible for technical leadership, hiring and supervising of
contractors, management of schedules, writing of reports, interaction
with the customer, and presention the work at technical meetings.
Member of Technical Staff, Xerox Imaging Systems (Peabody,
MA, 1991-1995)
- Designed and implemented the document page segmentation system
that was included in a range of products, from shrink-wrap software
packages (e.g., TextBridge) to reading machines for the blind
(The Reading Edge). System is capable of robustly segmenting
pages with complex layouts, and was rated most accurate segmentation
package on the market at the 1995 UNLV OCR accuracy contest
(University of Nevada in Las Vegas studies are a reference in the
Document Recognition world).
- Major contributor to several other pieces of XIS' document
recognition technology, including character recognition, page
filtering, binarization techniques, algorithmic and architectural
advances.
Harvard University, Robotics Laboratory |
1990-1991 |
Postdoctoral Fellow
- Published and extended the morphological algorithmic techniques
developed during my PhD work.
- Initiated collaborative work with some of the best researchers
in the field.
- Participated in the design of an image analysis software for the
Macintosh, DIP Station, distributed by the Hayden Image
Processing Group.
- Collaborated with Uniformed Services University of the Health
Sciences on segmentation, quantification, and modeling of corneal
endothelial tissue. Designed new technique for the direct estimation
of corneal healthiness via image analysis.
École Nationale Supérieure des Mines de Paris,
France |
1988-1990 |
Associate Research Fellow
- Worked towards my PhD degree, under the guidance of
Prof. Serra.
- Undertook new marketing efforts on behalf of the Center
for Mathematical Morphology; they led to contracts with two major
French institutions (the Aérospatiale Company and the French Institute for Petrol), which I supervised from beginning to
end.
Independent image analysis consultant since 1988. Clients in a
wide range of fields, including medical imaging, remote sensing,
automated inspection, optometry, oil exploration, etc. Some key
customers and projects include:
- Atlantic Aerospace Electronics Corporation, Waltham MA
(1991-93). Developed new algorithms for automatically extracting
correlogram tracks in sonar imagery. Algorithms are capable of
detecting tracks even under extremely low signal-to-noise ratios,
where other techniques would fail. Also designed
hierarchical watershed-based algorithms to robustly extract and
recognize targets in Forward-Looking Infrared (FLIR) imagery.
- Woods Hole Oceanographic Institution. Woods Hole, MA
(1992-99). Participated in the design of a system to automate the
detection and classification of plankton from towed video microscopy
sequences. Provided some of the key segmentation and feature
extraction algorithms used by the system.
- Vysis, Inc., Downers Grove, IL (1992-96). Developed
complex segmentation and pattern recognition algorithms aimed at
chromosome analysis from blood sample.
- Chevron Petroleum Technology Company, La Habra, CA
(1996-present). Proprietary project involving oil exploration and
requiring the processing of huge 3D data sets.
- Humphrey Systems, Dublin, CA (1998-1999). Developed key
image enhancement and feature extraction algorithms for ophthalmologic
instruments.
- Applied Imaging, Santa Clara, CA (1999). Designed novel
methods for discriminating between different classes of cells in
microscopy slides.
- Recognized expert in the field of Morphological Image
Analysis. Author of over 60 technical publications on various
aspects of morphology and of document recognition. While working at
ScanSoft, Xerox and LizardTech, remained active in the image analysis
community and frequently collaborated with some of the world's leading
researchers in the field.
Note: publications are available online at www.vincent-net.com/luc/papers/
- Associate editor, of the IEEE Transactions on Pattern
Analysis and Machine Intelligence (PAMI), 2000-2004, and of the
Journal of Electronic Imaging, 1994-2002.
- General chair for a number of conferences, including: new
SPIE conference on Document Recognition, held yearly in San
Jose, CA, since February 1994; IEEE Document Image Analysis
Workshop, held in San Juan, June 1997; upcoming International
Symposium on Mathematical Morphology, Palo Alto, June 2000. Also
chair and co-organizer of over a dozen other conferences since 1991.
- In spare time, writing a book entitled ``Morphology: a
Practical and Algorithmic Handbook for Image Analysis'', to be
published by Cambridge University Press.
- Reviewer for numerous journals and publishers since 1988,
including IEEE Trans. on Pattern Analysis and Machine
Intelligence, Journal of Visual Communication and Image
Representation, Signal Processing, IEEE Trans. on Acoustics, Speech
and Signal Processing, IEEE Trans. on Systems, Man and Cybernetics,
IEEE Trans. on Medical Imaging, IEEE Trans. on Image Processing,
Acta Stereologica, Journal of Mathematical Imaging, Journal of
Electronic Imaging, Oxford University Press.
- Invited as committee member for a number of Ph.D.
dissertations in the field of Computer Vision.
- Invited researcher and lecturer at some
of the world's most prestigious institutions, such as: France:
INRIA, Thomson's Central Research Laboratory, Philips Electronics
Laboratory, Aérospatiale, GE Medical Systems. The Netherlands:
CWI, TNO Institute for Perception. United States: Bell
Laboratories, Environmental Research Institute of Michigan (ERIM),
Rensselaer Polytechnic Institute,
Brown University, The John Hopkins University, Georgia Institute of
Technology, Siemens Corporate Research.
Australia: Commonwealth Scientific and Industrial Research
Organization (CSIRO).
Brazil: INPE (National Institute for Spatial Research)
and several Universities in Sao Paulo, Rio de Janeiro, and
Curitiba.
South Africa: University of Witwatersrand, DeBeers.
- Extensive teaching experience: dozens of short courses taught in
at least eight different countries since 1987.
- Patents:
- U.S. patent # 7266250 Methods for Generating Anti-Aliased
Text and Line Graphics in Compressed Document Images, issued
September 4, 2007 (co-inventors: D. Bloomberg and others)
- U.S. patent # 7069149 process for Interpreting Faults from
a Fault-Enhanced 2-Dimensional Seismic Attribute Volume, issued June
27, 2006 (co-inventors: D. Goff, K. Deal, W. Kowalik, S. Bombarde,
S. Lee. W. Voltz and R. Jones)
- U.S. patent # 5778092 Method and apparatus
for compressing color or gray scale documents, issued July 7, 1998
(co-inventors: P. Macleod and X. Zhu).
- Over a dozen additional patents pending.
- U.S. and French citizenships.
- Computer languages and environments: C, C++, JavaScript, Perl,
Lisp, cgi-bin, bash, csh, Matlab, Apache, TeX, etc. Administrator
level experience with Linux and Windows 2000/XP.
- Languages: French, native language; fluent in English and
German.
- Hobbies: rock climbing, hiking, biking, skiing, mountaineering
(successfully organized and led an expedition to the top of Mt
McKinley, Alaska, in June 1991), travel to remote places.