Opencv
Interim Chief Executive Officer
Sight Commerce Aug 2007 - Aug 2015
Founder and Chief Technology Officer
Big Vision Aug 2007 - Aug 2015
Founder and Partner
Kriegman-Belhumeur Vision Technologies Jan 2007 - Apr 2007
Research Scientist
University of California, San Diego Dec 1, 2001 - Sep 1, 2006
Research Assistant
Education:
Uc San Diego 2001 - 2006
Doctorates, Doctor of Philosophy, Electrical Engineering
Indian Institute of Technology, Kharagpur 1997 - 2001
Ravenshaw College 1995 - 1997
University of California
Kendriya Vidyalaya
Indian Institute of Technology Kharagpur
Skills:
Machine Learning Computer Vision Algorithms Image Processing C++ Python Matlab Opencv Programming C Entrepreneurship Artificial Intelligence Signal Processing Computer Science Research and Development R&D Apis Management Software Development Software Engineering
Taaz Inc. since Aug 2007
Founder / VP Technology
Kriegman-Belhumeur Vision Technologies Jan 2007 - Apr 2007
Research Scientist
University of California, San Diego Dec 2001 - Sep 2006
Research Assistant
The Scripps Research Institute 2005 - 2005
Research Assistant
Education:
University of California, San Diego 2001 - 2006
Ph.D., Computer Vision
Indian Institute of Technology, Kharagpur 1997 - 2001
B. Tech, Electrical Engineering
Ravenshaw College 1995 - 1997
Kendriya Vidyalaya
Skills:
Machine Learning Algorithms Entrepreneurship APIs Matlab Computer Vision C++ C Signal Processing Programming Image Processing
Languages:
Hindi
Us Patents
Methods For Identifying, Separating And Editing Reflection Components In Multi-Channel Images And Videos
Satya P. Mallick - La Jolla CA, US David J. Kriegman - San Diego CA, US Todd E. Zickler - Cambridge MA, US Peter N. Belhumeur - New York NY, US
Assignee:
The Regents of the University of California - Oakland CA
International Classification:
G06K 9/00
US Classification:
382163
Abstract:
The present invention presents a framework for separating specular and diffuse reflection components in images and videos. Each pixel of the an M-channel input image illuminated by N light sources is linearly transformed into a new color space having (M−N) channels. For an RGB image with one light source, the new color space has two color channels (U,V) that are free of specularities and a third channel (S) that contains both specular and diffuse components. When used with multiple light sources, the transformation may be used to produce a specular invariant image. A diffuse RGB image can be obtained by applying a non-linear partial differential equation to an RGB image to iteratively erode the specular component at each pixel. An optional third dimension of time may be added for processing video images. After the specular and diffuse components are separated, dichromatic editing may be used to independently process the diffuse and the specular components to add or suppress visual effects.
Satya P. Mallick - La Jolla CA, US David J. Kriegman - San Diego CA, US Todd E. Zickler - Cambridge MA, US Peter N. Belhumeur - New York NY, US
Assignee:
The Regents of the University of California - Oakland CA
International Classification:
G06K 9/00
US Classification:
382163
Abstract:
The present invention presents a framework for separating specular and diffuse reflection components in images and videos. Each pixel of the an M-channel input image illuminated by N light sources is linearly transformed into a new color space having (M−N) channels. For an RGB image with one light source, the new color space has two color channels (U,V) that are free of specularities and a third channel (S) that contains both specular and diffuse components. When used with multiple light sources, the transformation may be used to produce a specular invariant image. A diffuse RGB image can be obtained by applying a non-linear partial differential equation to an RGB image to iteratively erode the specular component at each pixel. An optional third dimension of time may be added for processing video images. After the specular and diffuse components are separated, dichromatic editing may be used to independently process the diffuse and the specular components to add or suppress visual effects.
Satya P. Mallick - San Diego CA, US Kevin Barnes - San Diego CA, US Margaret Rose Ciafardini Kirkland - New York NY, US Kristine Anna Dougherty - San Diego CA, US Deepu John - San Diego CA, US David Kriegman - San Diego CA, US Vipanj B. Patel - Centennial CO, US
Assignee:
Photometria, Inc - La Jolla CA
International Classification:
G09B 19/00
US Classification:
434100, 434 99
Abstract:
A system and method for providing a personalized face chart. A digital image of the subject's face is obtained. A facial region of the digital image is identified. A line drawing is generated based on at least the facial region of the digital image.
System And Method For Providing And Modifying A Personalized Face Chart
Douglas Fidaleo - San Diego CA, US Brent Foust - San Diego CA, US Jennifer Neuman - San Diego CA, US Satya Mallick - San Diego CA, US Kevin Barnes - San Diego CA, US David Kriegman - San Diego CA, US
Assignee:
Photometria, Inc. - La Jolla CA
International Classification:
G09B 19/00
US Classification:
434 99, 434100
Abstract:
A system and method for providing a personalized digital face chart. A digital image of a subject's face is obtained. A facial region of the digital image is identified from a background region of the digital image. A line drawing is generated based on at least the facial region of the digital image. The line drawing is stylized to generate a personalized digital face chart. A user interface configured to accept at least one face chart modification from a user is provided. The personalized digital face chart is modified based on the at least one face chart modification.
Graphical User Interface For Selection Of Options From Option Groups And Methods Relating To Same
Kevin Barnes - San Diego CA, US Satya Mallick - San Diego CA, US
Assignee:
PHOTOMETRIA, INC. - San Diego CA
International Classification:
G09G 5/02 G06F 3/048
US Classification:
345594, 715781
Abstract:
A system providing a graphical user interface for the selection of options from option groups and method for implementing the same. A graphical user interface enables a user to see the results of applying virtual makeup to an image of a person's face. The interface may enable a user to select the color of the makeup to be applied through a circular region with a series of option tabs. The outer portion of the circular region, or the flywheel, may have multiple color segments. The color segments are arranged so that adjacent color segments may be perceived to be most similar. The inner portion of the circle may present the history of the colors previously chosen and may have an uncolored center circle, and a series of uncolored circles surrounding the center circle.
Method Of Monetizing Online Personal Beauty Product Selections
Satya Mallick - San Diego CA, US Kevin Barnes - San Diego CA, US Vipanj Patel - Centennial CO, US Deepu John - San Diego CA, US David Kriegman - San Diego CA, US
Assignee:
PHOTOMETRIA, INC. - San Diego CA
International Classification:
G06Q 30/00 G06Q 99/00
US Classification:
705 10, 705 27, 705 14, 705 37, 705 1
Abstract:
One or more embodiments of the program are directed to a plurality of methods for monetizing online personalized beauty product selections utilizing a technology for content-targeted Internet advertising on a virtual makeover website. Methods comprise: (1) categorizing facial features to select product advertisements for co-branding in a product palette; (2) an auction for webpage advertisement placements related to a user's facial features; (3) transforming a makeover “look” to advertise alternative products to produce the new look under different lighting conditions; (4) a gifting system to allow sale and gifting of products used to produce a makeover, where the makeover image may be packaged with the selected products in a gift package; and (5) recapturing users who would cancel a sale with an offer of less expensive comparable products.
System And Method For Changing Hair Color In Digital Images
Satya P. Mallick - San Diego CA, US Hui Qiao - San Diego CA, US David Kriegman - San Diego CA, US
International Classification:
G09G 5/02
US Classification:
345594
Abstract:
A system and method for digital hair coloring is described. A starting image of a subject including a hair region is obtained. At least one foreground selection of the starting image is obtained, the foreground selection including a portion of the hair region. At least one background selection of the starting image excluding the hair region is obtained. A matte defining a calculated foreground area of the starting image is calculated based on the foreground selection and the background selection. A target color distribution based on a target hair color is obtained. A color image is generated by applying a color transformation based on the target color distribution to at least the calculated foreground area of the starting image. An output image is generated from the colored image and the starting image.
Systems And Methods For Simulating Accessory Display On A Subject
Matthew Flagg - San Diego CA, US Satya Mallick - San Diego CA, US David Kriegman - San Diego CA, US
International Classification:
G09G 5/00
US Classification:
345629
Abstract:
Systems and methods for simulating accessory display on a subject are described herein. At least one digital image of a subject is obtained. At least one target contour in an accessory target zone is identified. An accessory image and an accessory foreground matte, and a plurality of accessory control points associated with at least one contour contact zone are obtained. At least one accessory scaling factor is determined. At least one accessory registration angle is determined based on the at least one digital image. At least one simulated image is generated by registering a foreground portion of the accessory image with the at least one digital image based on the at least one accessory scaling factor, the at least one accessory registration angle, the accessory foreground matte, the at least one target contour, and the plurality of accessory control points, where registering includes applying a transformation.