Search

Peyman P Milanfar

from Menlo Park, CA
Age ~58

Peyman Milanfar Phones & Addresses

  • 924 Timothy Ln, Menlo Park, CA 94025 (650) 329-1371
  • Somerville, MA
  • Oakland, CA
  • Cambridge, MA
  • San Mateo, CA
  • 924 Timothy Ln, Menlo Park, CA 94025

Work

Company: Uc santa cruz Jul 1999 to Nov 2014 Position: Professor of electrical engineering

Education

Degree: Master of Science, Doctorates, Masters, Doctor of Philosophy School / High School: Massachusetts Institute of Technology 1989 to 1993

Skills

Image Processing • Video Processing • Computer Vision • Signal Processing • Machine Learning • Algorithms • Mathematical Modeling • Applied Mathematics • Pattern Recognition • Computer Science • Artificial Intelligence • Scientific Computing • Software Engineering

Languages

English • Spanish

Industries

Research

Resumes

Resumes

Peyman Milanfar Photo 1

Principal Scientist And Director

View page
Location:
Menlo Park, CA
Industry:
Research
Work:
Uc Santa Cruz Jul 1999 - Nov 2014
Professor of Electrical Engineering

Google Jul 1999 - Nov 2014
Principal Scientist and Director

Uc Santa Cruz Jun 2010 - Jul 2012
Associate Dean For Research and Graduate Studies

Motiondsp Jan 2005 - Jan 2006
Founder and Chief Technology Officer

Stanford University 1998 - 2000
Consulting Professor of Computer Science
Education:
Massachusetts Institute of Technology 1989 - 1993
Master of Science, Doctorates, Masters, Doctor of Philosophy
University of California, Berkeley 1984 - 1988
Bachelors, Bachelor of Science, Electrical Engineering, Mathematics
Skills:
Image Processing
Video Processing
Computer Vision
Signal Processing
Machine Learning
Algorithms
Mathematical Modeling
Applied Mathematics
Pattern Recognition
Computer Science
Artificial Intelligence
Scientific Computing
Software Engineering
Languages:
English
Spanish

Publications

Us Patents

Dynamic Reconstruction Of High-Resolution Video From Color-Filtered Low-Resolution Video-To-Video Super-Resolution

View page
US Patent:
7379612, May 27, 2008
Filed:
Oct 19, 2006
Appl. No.:
11/584400
Inventors:
Peyman Milanfar - Menlo Park CA, US
Michael Elad - Haifa, IL
Assignee:
The Regents of the University of California, Santa Cruz - Oakland CA
International Classification:
G06K 9/40
US Classification:
382254, 382167, 382169, 382299
Abstract:
A method is provided of solving the dynamic super-resolution (SR) problem of reconstructing a high-quality set of monochromatic or color superresolved images from low-quality monochromatic, color, or mosaiced frames. The invention includes a joint method for simultaneous SR, deblurring, and demosaicing, this way taking into account practical color measurements encountered in video sequences. For the case of translational motion and common space-invariant blur, the proposed invention is based on a very fast and memory efficient approximation of the Kalman filter (KF). Experimental results on both simulated and real data are supplied, demonstrating the invention algorithms, and their strength.

System And Method For Robust Multi-Frame Demosaicing And Color Super-Resolution

View page
US Patent:
7412107, Aug 12, 2008
Filed:
Dec 12, 2005
Appl. No.:
11/301811
Inventors:
Peyman Milanfar - Menlo Park CA, US
Michael Elad - Halfa, IL
Assignee:
The Regents of the University of California, Santa Cruz - Oakland CA
International Classification:
G06K 9/40
US Classification:
382254, 382300, 382263, 345606
Abstract:
An integrated method for both super-resolution and multi-frame demosaicing includes an image fusion followed by simultaneous deblurring and interpolation. For the case of color super-resolution, the first step involves application of recursive image fusion separately on the three different color layers. The second step is based on minimizing a maximum a posteriori (MAP) cost function. In one embodiment, the MAP cost function is composed of several terms: a data fidelity penalty term that penalizes dissimilarity between the raw data and the super-resolved estimate, a luminance penalty term that favors sharp edges in the luminance component of the image, a chrominance penalty term that favors low spatial frequency changes in the chrominance component of the image, and an orientation penalty term that favors similar edge orientations across the color channels. The method is also applicable to color super-resolution (without demosaicing), where the low-quality input images are already demosaiced. In addition, for translational motion, the method may be used in a very fast image fusion algorithm to facilitate the implementation of dynamic, multi-input/multi-output color super-resolution/demosaicing.

Robust Reconstruction Of High Resolution Grayscale Images From A Sequence Of Low Resolution Frames

View page
US Patent:
7477802, Jan 13, 2009
Filed:
Nov 16, 2006
Appl. No.:
11/601518
Inventors:
Peyman Milanfar - Menlo Park CA, US
Michael Elad - Haifa, IL
Michael D. Robinson - Menlo Park CA, US
Assignee:
The Regents of the University of California, Santa Cruz - Oakland CA
International Classification:
G06K 9/32
US Classification:
382299, 382266, 382274, 382275, 358 12, 358 326, 358 327
Abstract:
A computer method of creating a super-resolved grayscale image from lower-resolution images using an Lnorm data fidelity penalty term to enforce similarities between low and a high-resolution image estimates is provided. A spatial penalty term encourages sharp edges in the high-resolution image, the data fidelity penalty term is applied to space invariant point spread function, translational, affine, projective and dense motion models including fusing the lower-resolution images, to estimate a blurred higher-resolution image and then a deblurred image. The data fidelity penalty term uses the Lnorm in a likelihood fidelity term for motion estimation errors. The spatial penalty term uses bilateral-TV regularization with an image having horizontal and vertical pixel-shift terms, and a scalar weight between 0 and 1. The penalty terms create an overall cost function having steepest descent optimization applied for minimization. Direct image operator effects replace matrices for speed and efficiency.

Efficient Method To Predict Integrated Circuit Temperature And Power Maps

View page
US Patent:
7627841, Dec 1, 2009
Filed:
Apr 12, 2007
Appl. No.:
11/787108
Inventors:
Ali Shakouri - Santa Cruz CA, US
Travis Kemper - Mission Viejo CA, US
Yan Zhang - Santa Cruz CA, US
Peyman Milanfar - Menlo Park CA, US
Xi Wang - Santa Cruz CA, US
Assignee:
The Regents of the University of California, Santa Cruz - Oakland CA
International Classification:
G06F 17/50
H01L 21/66
US Classification:
716 4, 438 17
Abstract:
The temperature distribution associated with a design of an integrated circuit is calculated by convoluting a surface power usage represented by a power matrix with a heat spreading function. The heat spreading function may be calculated from a simulation of a point source on the integrated circuit using a finite element analysis model of the integrated circuit or other techniques. To account for spatial variations on the chip, the heat spreading function may be made dependent on position using a position scaling function. Steady-state or transient temperature distributions may be computed by using a steady-state or transient heat spreading function. A single heat spreading function may be convolved with various alternative power maps to efficiently calculate temperature distributions for different designs. In an inverse problem, one can calculate the power map from an empirically measured temperature distribution and a heat spreading function using various de-convolution techniques. While the forward problem is analogous to image blurring, the inverse problem is analogous to image restoration.

Kernel Regression For Image Processing And Reconstruction

View page
US Patent:
7889950, Feb 15, 2011
Filed:
Aug 30, 2006
Appl. No.:
11/513833
Inventors:
Peyman Milanfar - Menlo Park CA, US
Hiroyuki Takeda - Santa Cruz CA, US
Assignee:
The Regents of the University of California, Santa Cruz - Oakland CA
International Classification:
G06K 9/32
H04N 7/01
H04N 5/00
US Classification:
382300, 348624, 348441
Abstract:
A method of image processing using kernel regression is provided. An image gradient is estimated from original data that is analyzed for local structures by computing a scaling parameter, a rotation parameter and an elongation parameter using singular value decomposition on local gradients of the estimated gradients locally to provide steering matrices. A steering kernel regression having steering matrices is applied to the original data to provide a reconstructed image and new image gradients. The new gradients are analyzed using singular value decomposition to provide new steering matrices. The steering kernel regression with the new steering matrices is applied to the noisy data to provide a new reconstructed image and further new gradients. The last two steps are repeated up to ten iterations to denoise the original noisy data and improve the local image structure.

System And Method For Robust Multi-Frame Demosaicing And Color Super Resolution

View page
US Patent:
7940282, May 10, 2011
Filed:
Aug 17, 2006
Appl. No.:
11/506246
Inventors:
Peyman Milanfar - Menlo Park CA, US
Michael Elad - Halfa, IL
Assignee:
The Regents of the University of California, Santa Cruz - Oakland CA
International Classification:
G09G 5/00
G09G 5/02
H04N 9/04
H04N 5/00
H03L 7/00
G03F 3/08
G06K 9/00
H04N 1/46
G06K 9/40
G06K 9/32
US Classification:
345606, 345589, 345611, 345643, 345616, 348273, 348538, 348606, 348607, 358512, 358518, 358525, 382162, 382254, 382263, 382300
Abstract:
A method of creating a super-resolved color image from multiple lower-resolution color images is provided by combining a data fidelity penalty term, a spatial luminance penalty term, a spatial chrominance penalty term, and an inter-color dependencies penalty term to create an overall cost function. The data fidelity penalty term is an L1 norm penalty term to enforce similarities between raw data and a high-resolution image estimate, the spatial luminance penalty term is to encourage sharp edges in a luminance component to the high-resolution image, the spatial chrominance penalty term is to encourage smoothness in a chrominance component of the high-resolution image, and the inter-color dependencies penalty term is to encourage homogeneity of an edge location and orientation in different color bands. A steepest descent optimization is applied to the overall cost function for minimization by applying a derivative to each color band while the other color bands constant.

Training-Free Generic Object Detection In 2-D And 3-D Using Locally Adaptive Regression Kernels

View page
US Patent:
8559671, Oct 15, 2013
Filed:
Dec 16, 2009
Appl. No.:
12/998965
Inventors:
Peyman Milanfar - Menlo Park CA, US
Hae Jong Seo - Santa Cruz CA, US
Assignee:
The Regents of the University of California - Oakland CA
International Classification:
G06K 9/00
US Classification:
382103, 382154, 382224
Abstract:
The present invention provides a method of learning-free detection and localization of actions that includes providing a query video action of interest and providing a target video, obtaining at least one query space-time localized steering kernel (3-D LSK) from the query video action of interest and obtaining at least one target 3-D LSK from the target video, determining at least one query feature from the query 3-D LSK and determining at least one target patch feature from the target 3-D LSK, and outputting a resemblance map, where the resemblance map provides a likelihood of a similarity between each the query feature and each target patch feature to output learning-free detection and localization of actions, where the steps of the method are performed by using an appropriately programmed computer.

Submicron Thermal Imaging Method And Enhanced Resolution (Super-Resolved) Ac-Coupled Imaging For Thermal Inspection Of Integrated Circuits

View page
US Patent:
20020126732, Sep 12, 2002
Filed:
Jan 4, 2002
Appl. No.:
10/039290
Inventors:
Ali Shakouri - Santa Cruz CA, US
Peyman Milanfar - Menlo Park CA, US
Kenneth Pedrotti - Soquel CA, US
James Christofferson - Santa Cruz CA, US
Assignee:
THE REGENTS OF THE UNIVERSITY OF CALIFORNIA
International Classification:
G01J005/00
US Classification:
374/130000
Abstract:
Methods and apparatus for non-contact thermal measurement which are capable of providing sub micron surface thermal characterization of samples, such as active semiconductor devices. The method obtains thermal image information by reflecting a light from a surface of a device in synchronous with the modulation of the thermal excitation and then acquiring and processing an AC-coupled thermoreflective image. The method may be utilized for making measurements using different positioning techniques, such as point measurements, surface scanning, two-dimensional imaging, and combinations thereof. A superresolution method is also described for increasing the resultant image resolution, based on multiple images with fractional pixel offsets, without the need to increase the resolution of the image detectors being utilized. The thermoreflective method provides a spatial resolution better than current infrared cameras, operates within a wide temperature range, and is capable of a thermal resolution on the order of 10 mK.
Peyman P Milanfar from Menlo Park, CA, age ~58 Get Report