Search For:

Displaying 1-49 out of 49 total
Extracting volumetric information from standard two-dimensional radiological annotations within the clinical workflow
Found in: 2012 IEEE International Conference on Bioinformatics and Biomedicine Workshops (BIBMW)
By Sharmili Roy,Michael S. Brown,George L. Shih
Issue Date:October 2012
pp. 725-731
In a typical radiological reporting workflow, radiologists make image-based annotations to denote regions of clinical significance or to perform quantitative measurements. Interestingly, virtually all annotation software allow only 2D geometric primitives ...
 
Offline Mobile Instance Retrieval with a Small Memory Footprint
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Jayaguru Panda,Michael S. Brown,C.V. Jawahar
Issue Date:December 2013
pp. 1257-1264
Existing mobile image instance retrieval applications assume a network-based usage where image features are sent to a server to query an online visual database. In this scenario, there are no restrictions on the size of the visual database. This paper, how...
 
Geometric and Shading Correction for Images of Printed Materials: A Unified Approach Using Boundary
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Yau-Chat Tsoi, Michael S. Brown
Issue Date:July 2004
pp. 240-246
We present a novel approach that uses boundary interpolation to correct (1) geometric distortion and (2) shading artifacts present in images of printed materials. Unlike existing approaches, our algorithm can simultaneously correct a variety of geometric d...
 
High quality depth map upsampling for 3D-TOF cameras
Found in: Computer Vision, IEEE International Conference on
By Jaesik Park,Hyeongwoo Kim, Yu-Wing Tai,Michael S. Brown,Inso Kweon
Issue Date:November 2011
pp. 1623-1630
This paper describes an application framework to perform high quality upsampling on depth maps captured from a low-resolution and noisy 3D time-of-flight (3D-ToF) camera that has been coupled with a high-resolution RGB camera. Our framework is inspired by ...
 
Image/video deblurring using a hybrid camera
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Yu-Wing Tai, Hao Du, Michael S. Brown, Stephen Lin
Issue Date:June 2008
pp. 1-8
We propose a novel approach to reduce spatially varying motion blur using a hybrid camera system that simultaneously captures high-resolution video at a low-frame rate together with low-resolution video at a high-frame rate. Our work is inspired by Ben-Ezr...
 
Robust Estimation of Texture Flow via Dense Feature Sampling
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Yu-Wing Tai, Michael S. Brown, Chi-Keung Tang
Issue Date:June 2007
pp. 1-8
Texture flow estimation is a valuable step in a variety of vision related tasks, including texture analysis, image segmentation, shape-from-texture and texture remapping. This paper describes a novel and effective technique to estimate texture flow in an i...
 
Revisiting radiometric calibration for color computer vision
Found in: Computer Vision, IEEE International Conference on
By Haiting Lin, Seon Joo Kim,Sabine Susstrunk,Michael S. Brown
Issue Date:November 2011
pp. 129-136
We present a study of radiometric calibration and the in-camera imaging process through an extensive analysis of more than 10,000 images from over 30 cameras. The goal is to investigate if image values can be transformed to physically meaningful values and...
 
Motion Regularization for Matting Motion Blurred Objects
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Hai Ting Lin,Yu-Wing Tai,Michael S. Brown
Issue Date:November 2011
pp. 2329-2336
This paper addresses the problem of matting motion blurred objects from a single image. Existing single image matting methods are designed to extract static objects that have fractional pixel occupancy. This arises because the physical scene object has a f...
 
Super resolution using edge prior and single image detail synthesis
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Yu-Wing Tai, Shuaicheng Liu, Michael S. Brown, Stephen Lin
Issue Date:June 2010
pp. 2400-2407
Edge-directed image super resolution (SR) focuses on ways to remove edge artifacts in upsampled images. Under large magnification, however, textured regions become blurred and appear homogenous, resulting in a super-resolution image that looks unnatural. A...
 
A framework for ultra high resolution 3D imaging
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Zheng Lu, Yu-Wing Tai, Moshe Ben-Ezra, Michael S. Brown
Issue Date:June 2010
pp. 1205-1212
We present an imaging framework to acquire 3D surface scans at ultra high-resolutions (exceeding 600 samples per mm<sup>2</sup>). Our approach couples a standard structured-light setup and photometric stereo using a large-format ultra-high-reso...
 
Example-Based Cosmetic Transfer
Found in: Computer Graphics and Applications, Pacific Conference on
By Wai-Shun Tong, Chi-Keung Tang, Michael S. Brown, Ying-Qing Xu
Issue Date:November 2007
pp. 211-218
<p>Cosmetic makeup is used worldwide as a means to enhance beauty and express moods. An art form in its own right, cosmetic styles continuously change and evolve to reflect cultural and societal trends. While countless magazines and books are dedicat...
 
Richardson-Lucy Deblurring for Scenes under a Projective Motion Path
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Yu-Wing Tai, Ping Tan, Michael S. Brown
Issue Date:August 2011
pp. 1603-1618
This paper addresses how to model and correct image blur that arises when a camera undergoes ego motion while observing a distant scene. In particular, we discuss how the blurred image can be modeled as an integration of the clear scene under a sequence of...
 
Globally Optimized Linear Windowed Tone Mapping
Found in: IEEE Transactions on Visualization and Computer Graphics
By Qi Shan, Jiaya Jia, Michael S. Brown
Issue Date:July 2010
pp. 663-675
This paper introduces a new tone mapping operator that performs local linear adjustments on small overlapping windows over the entire input image. While each window applies a local linear adjustment that preserves the monotonicity of the radiance values, t...
 
Correction of Spatially Varying Image and Video Motion Blur Using a Hybrid Camera
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Yu-Wing Tai, Hao Du, Michael S. Brown, Stephen Lin
Issue Date:June 2010
pp. 1012-1028
We describe a novel approach to reduce spatially varying motion blur in video and images using a hybrid camera system. A hybrid camera is a standard video camera that is coupled with an auxiliary low-resolution camera sharing the same optical path but capt...
 
Image Restoration of Arbitrarily Warped Documents
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Michael S. Brown, W. Brent Seales
Issue Date:October 2004
pp. 1295-1306
We present a framework for acquiring and restoring images of warped documents. The purpose of our restoration is to create a planar representation of a once planar document that has undergone an arbitrary and unknown rigid deformation. To accomplish this r...
 
Multi-Projector Displays Using Camera-Based Registration
Found in: Visualization Conference, IEEE
By Ramesh Raskar, Michael S. Brown, Ruigang Yang, Wei-Chao Chen, Greg Welch, Herman Towles, Brent Seales, Henry Fuchs
Issue Date:October 1999
pp. 26
<div>Conventional projector-based display systems are typically designed around precise and regular configurations of projectors and display surfaces. While this results in rendering simplicity and speed, it also means painstaking construction and on...
 
Quick Approximation of Camera's Spectral Response from Casual Lighting
Found in: 2013 IEEE International Conference on Computer Vision Workshops (ICCVW)
By Dilip K. Prasad,Rang Nguyen,Michael S. Brown
Issue Date:December 2013
pp. 844-851
Knowing the RGB spectral sensitivities of a camera is useful for several image processing applications. However, camera manufacturers seldom provide this information. Calibration methods for determining them can be daunting, requiring either sophisticated ...
 
A Learning-Based Approach to Reduce JPEG Artifacts in Image Matting
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Inchang Choi,Sunyeong Kim,Michael S. Brown,Yu-Wing Tai
Issue Date:December 2013
pp. 2880-2887
Single image matting techniques assume high-quality input images. The vast majority of images on the web and in personal photo collections are encoded using JPEG compression. JPEG images exhibit quantization artifacts that adversely affect the performance ...
 
Exploiting Reflection Change for Automatic Reflection Removal
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Yu Li,Michael S. Brown
Issue Date:December 2013
pp. 2432-2439
This paper introduces an automatic method for removing reflection interference when imaging a scene behind a glass surface. Our approach exploits the subtle changes in the reflection with respect to the background in a small set of images taken at slightly...
 
Ink-bleed reduction using functional minimization
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Grani A. Hanasusanto, Zheng Wu, Michael S. Brown
Issue Date:June 2010
pp. 825-832
Ink-bleed interference is undesirable as it reduces the legibility and aesthetics of affected documents. We present a novel approach to reduce ink-bleed interference using functional minimization. In particular, we show how to modify the Chan-Vese active c...
 
Automatic Corresponding Control Points Selection for Historical Document Image Registration
Found in: Document Analysis and Recognition, International Conference on
By Jie Wang, Michael S. Brown, Chew Lim Tan
Issue Date:July 2009
pp. 1176-1180
Image registration is crucial for various image analysis tasks. In particular, most approaches to correction of bleed-through distortion on handwritten document images require the recto image and the verso image to be precisely registered. In this paper, w...
 
Accurate Alignment of Double-Sided Manuscripts for Bleed-Through Removal
Found in: Document Analysis Systems, IAPR International Workshop on
By Jie Wang, Michael S. Brown, Chew Lim Tan
Issue Date:September 2008
pp. 69-75
Double-sided manuscripts are often degraded by bleed-through interference. Such degradation must be corrected to facilitate human perception and machine recognition. Most approaches to bleed-through removal rely on perfect alignment between the recto and v...
 
A framework for reducing ink-bleed in old documents
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Yi Huangy, Michael S. Brown, Dong Xuy
Issue Date:June 2008
pp. 1-7
We describe a novel application framework to reduce the effects of ink-bleed in old documents. This task is treated as a classification problem where training-data is used to compute per-pixel likelihoods for use in a dual-layer Markov Random Field (MRF) t...
 
Restoring 2D Content from Distorted Documents
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Michael S. Brown, Mingxuan Sun, Ruigang Yang, Lin Yun, W. Brent Seales
Issue Date:November 2007
pp. 1904-1916
This paper presents a framework to restore the 2D content printed on documents in the presence of geometric distortion and non-uniform illumination. Compared with textbased document imaging approaches that correct distortion to a level necessary to obtain ...
 
Multi-View Document Rectification using Boundary
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Yau-Chat Tsoi, Michael S. Brown
Issue Date:June 2007
pp. 1-8
We present a novel technique that uses multiple images of bound and folded documents to rectify the imaged content such that it appears flat and photometrically uniform. Our approach works from a sparse set of uncalibrated views of the document which are m...
 
Image Pre-Conditioning for Out-of-Focus Projector Blur
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Michael S. Brown, Peng Song, Tat-Jen Cham
Issue Date:June 2006
pp. 1956-1963
We present a technique to reduce image blur caused by out-of-focus regions in projected imagery. Unlike traditional restoration algorithms that operate on a blurred image to recover the original, the nature of our problem requires that the correction be ap...
 
Geometric and Photometric Restoration of Distorted Documents
Found in: Computer Vision, IEEE International Conference on
By Mingxuan Sun, Ruigang Yang, Yun Lin, George Landon, Brent Seales, Michael S. Brown
Issue Date:October 2005
pp. 1117-1123
We present a system to restore the 2D content printed on distorted documents. Our system works by acquiring a 3D scan of the document?s surface together with a high-resolution image. Using the 3D surface information and the 2D image, we can ameliorate unwa...
 
Conformal Deskewing of Non-Planar Documents
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Michael S. Brown, Charles J. Pisula
Issue Date:June 2005
pp. 998-1004
This paper presents an approach that uses conformal mapping to parameterize a document?s 3D shape to a 2D plane. Using this conformal parametrization, a restorative mapping between an image of the distorted document and a
 
A Practical and Flexible Tiled Display System
Found in: Computer Graphics and Applications, Pacific Conference on
By Michael S. Brown, W. Brent Seales
Issue Date:October 2002
pp. 194
<p>Computer graphics and high-resolution digital imagery are becoming increasingly pervasive in communities not traditionally associated with graphics. Commodity graphics cards and digital cameras, along with powerful modeling software, allow organiz...
 
PixelFlex: A Reconfigurable Multi-Projector Display System
Found in: Visualization Conference, IEEE
By Ruigang Yang, David Gotz, Justin Hensley, Herman Towles, Michael S. Brown
Issue Date:October 2001
pp. N/A
This paper presents PixelFlex - a spatially reconfigurable multi-projector display system. The PixelFlex system is composed of ceiling-mounted projectors, each with computer-controlled pan, tilt, zoom and focus; and a camera for closed-loop calibration. Wo...
 
Document Restoration Using 3D Shape: A General Deskewing Algorithm for Arbitrarily Warped Documents
Found in: Computer Vision, IEEE International Conference on
By Michael S. Brown, W. Brent Seales
Issue Date:July 2001
pp. 367
We present a framework for restoring arbitrarily warped and deformed documents to their original planar shape. The impetus for this work is the need for tools and techniques to help digitally preserve and restore fragile manuscripts. Current digitization i...
 
The Digital Atheneum: New Approaches for Preserving, Restoring and Analyzing Damaged Manuscripts
Found in: Digital Libraries, Joint Conference on
By Michael S. Brown, W. Brent Seales
Issue Date:June 2001
pp. 437-443
This paper presents research focused on developing new techniques and algorithms for the digital acquisition, restoration, and study of damaged manuscripts. We present results from an acquisition effort in partnership with the British Library, funded throu...
 
Projected Imagery in Your
Found in: IEEE Computer Graphics and Applications
By Greg Welch, Henry Fuchs, Ramesh Raskar, Herman Towles, Michael S. Brown
Issue Date:July 2000
pp. 62-67
Someday, high-resolution projected imagery will surround you in your office. The walls, your desk, and even the floor will serve as your computer desktop. Our dream is that your office will have ceiling-mounted digital cameras and projectors that work toge...
 
As-Projective-As-Possible Image Stitching with Moving DLT
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Julio Zaragoza,Tat-Jun Chin,Quoc-Huy Tran,Michael S. Brown,David Suter
Issue Date:July 2014
pp. 1-1
The success of commercial image stitching tools often leads to the impression that image stitching is a “solved problem”. The reality, however, is that many tools give unconvincing results when the input photos violate fairly restrictive imaging assumption...
 
As-Projective-As-Possible Image Stitching with Moving DLT
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Julio Zaragoza,Tat-Jun Chin,Michael S. Brown,David Suter
Issue Date:June 2013
pp. 2339-2346
We investigate projective estimation under model inadequacies, i.e., when the underpinning assumptions of the projective model are not fully satisfied by the data. We focus on the task of image stitching which is customarily solved by estimating a projecti...
 
An evaluation of wearable activity monitoring devices
Found in: Proceedings of the 1st ACM international workshop on Personal data meets distributed multimedia (PDM '13)
By Fangfang Guo, Michael S. Brown, Mohan S. Kankanhalli, Yu Li
Issue Date:October 2013
pp. 31-34
This paper examines an increasingly relevant topic in the multimedia community of wearable devices that record the physical activity of a user throughout a day. While activity and other accelerometry-based data has been shown effective in various multimedi...
     
Fast rotation search for real-time interactive point cloud registration
Found in: Proceedings of the 18th meeting of the ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games (I3D '14)
By Álvaro Parra Bustos, David Suter, Michael S. Brown, Tat-Jun Chin
Issue Date:March 2014
pp. 55-62
Our goal is the registration of multiple 3D point clouds obtained from LIDAR scans of underground mines. Such a capability is crucial to the surveying and planning operations in mining. Often, the point clouds only partially overlap and initial alignment i...
     
An interactive editing tool for correcting panoramas
Found in: SIGGRAPH Asia 2012 Technical Briefs (SA '12)
By Junhong Gao, Michael S. Brown
Issue Date:November 2012
pp. 1-4
Constructing panoramas from an image series is a fundamental task for photo-editing. State-of-the-art photo-editing softwares generally provide automatic stitching routines that first perform image warping followed by seam-cutting or blending to hide misal...
     
Imaging buddhist art with a digital large-format camera: A field study report from the dunhuang caves
Found in: Journal on Computing and Cultural Heritage (JOCCH)
By Michael S. Brown, Moshe Ben-Ezra, Wei Luo, Zheng Lu, Zhijun Sun
Issue Date:October 2012
pp. 1-10
This article describes recent field work undertaken by Microsoft Research Asia and the Dunhuang Academy to capture high-resolution images of Buddhist art at the UNESCO world heritage site, the Mogao Caves. This project is intended as a feasibility study ex...
     
Matting and compositing of transparent and refractive objects
Found in: ACM Transactions on Graphics (TOG)
By Chi-Keung Tang, Michael S. Brown, Sai-Kit Yeung, Sing Bing Kang
Issue Date:January 2011
pp. 1-13
This article introduces a new approach for matting and compositing transparent and refractive objects in photographs. The key to our work is an image-based matting model, termed the Attenuation-Refraction Matte (ARM), that encodes plausible refractive prop...
     
Motion regularization for matting motion blurred objects
Found in: ACM SIGGRAPH 2010 Talks (SIGGRAPH '10)
By Lin Hai Ting, Michael S. Brown, Tai Yu-Wing
Issue Date:July 2010
pp. 1-1
We address the problem of matting motion blurred objects from a single image. Existing single-image matting methods are designed to extract static objects that have fractional pixel occupancy. This arises because the real scene object has a finer resolutio...
     
BinarizationShop: a user-assisted software suite for converting old documents to black-and-white
Found in: Proceedings of the 10th annual joint conference on Digital libraries (JCDL '10)
By Fanbo Deng, Michael S. Brown, Zheng Lu, Zheng Wu
Issue Date:June 2010
pp. 255-258
Converting a scanned document to a binary format (black and white) is a key step in the digitization process. While many existing binarization algorithms operate robustly for well-kept documents, these algorithms often produce less than satisfactory result...
     
Texture amendment: reducing texture distortion in constrained parameterization
Found in: ACM Transactions on Graphics (TOG)
By Chi-Keung Tang, Heung-Yeung Shum, Michael S. Brown, Yu-Wing Tai
Issue Date:December 2008
pp. 1-49
Constrained parameterization is an effective way to establish texture coordinates between a 3D surface and an existing image or photograph. A known drawback to constrained parameterization is visual distortion that arises when the 3D geometry is mismatched...
     
User-assisted ink-bleed correction for handwritten documents
Found in: Proceedings of the 8th ACM/IEEE-CS joint conference on Digital libraries (JCDL '08)
By Michael S. Brown, Yi Huang
Issue Date:June 2008
pp. 597-617
We describe a user-assisted framework for correcting ink-bleed in old handwritten documents housed at the National Archives of Singapore (NAS). Our approach departs from traditional correction techniques that strive for full automation. Fully-automated app...
     
ShapePalettes: interactive normal transfer via sketching
Found in: ACM Transactions on Graphics (TOG)
By Chi-Keung Tang, Heung-Yeung Shum, Michael S. Brown, Tai-Pang Wu
Issue Date:July 2007
pp. 1-35
We present a simple interactive approach to specify 3D shape in a single view using "shape palettes". The interaction is as follows: draw a simple 2D primitive in the 2D view and then specify its 3D orientation by drawing a corresponding primitive on a sha...
     
The digital atheneum: new approaches for preserving, restoring and analyzing damaged manuscripts
Found in: Proceedings of the first ACM/IEEE-CS joint conference on Digital libraries (JCDL '01)
By Michael S. Brown, W. Brent
Issue Date:January 2001
pp. 437-443
This paper presents research focused on developing new techniques and algorithms for the digital acquisition, restoration, and study of damaged manuscripts. We present results from an acquisition effort in partnership with the British Library, funded thr...
     
Beyond 2D images: effective 3D imaging for library materials
Found in: Proceedings of the fifth ACM conference on Digital libraries (DL '00)
By Michael S. Brown, W. Brent Seales
Issue Date:June 2000
pp. 27-36
Significant efforts are being made to digitize rare and valuable library materials, with the goal of providing patrons and historians digital facsimiles that capture the "look and feel" of the original materials. This is often done by digitally photographi...
     
Geometrically correct imagery for teleconferencing
Found in: Proceedings of the seventh ACM international conference on Multimedia (Part 1) (MULTIMEDIA '99)
By Henry Fuchs, Michael S. Brown, Ruigang Yang, W. Brent Seales
Issue Date:October 1999
pp. 179-186
Current camera-monitor teleconferencing applications produce unrealistic imagery and break any sense of presence for the participants. Other capture/display technologies can be used to provide more compelling teleconferencing. However, complex geometries i...
     
Building large-format displays for digital libraries
Found in: Communications of the ACM
By Christopher O. Jaynes, Michael S. Brown, Stephen B. Webb, W. Brent Seales
Issue Date:January 1988
pp. 57-59
Case study findings from several corporate environments suggest that successful virtualization does not depend on the degree of technological sophistication. It's how the tools are used that matters.
     
 1