Home
Carlos Santos's Library tagged → View Popular
r-opencv - Project Hosting on Google Code
"r-opencv is part of the BioVision project, which aims at providing advanced image and video analysis abilities in R and Bioconductor backended by OpenCV, a popular computer vision library. "
MIT OpenCourseWare | Media Arts and Sciences | MAS.963 Special Topics: Computational Camera and Photography, Fall 2008 | Home
In this course we will study this emerging multi-disciplinary field at the intersection of signal processing, applied optics, computer graphics and vision, electronics, art, and online sharing through social networks. If novel cameras can be designed to sample light in radically new ways, then rich and useful forms of visual information may be recorded — beyond those present in traditional photographs. Furthermore, if computational process can be made aware of these novel imaging models, them the scene can be analyzed in higher dimensions and novel aesthetic renderings of the visual information can be synthesized.
The Rawseeds Project
The aim of the Rawseeds Project is to build benchmarking tools for robotic systems. This is done through the publication of a comprehensive, high-quality Benchmarking Toolkit
Bundler - Structure from Motion for Unordered Image Collections
Bundler is a structure-from-motion system for unordered image collections (for instance, images from the Internet).
Robotics Institute: Deception Detection
The aim of this project is to objectively extract facial-expression and body-gesture indicators of intention and deception using unobtrusive remote sensors such as video surveillance.
Computer Vision: Algorithms and Applications
I thought I had bookmarked it already: Richard Szeliski's (of Photosynth fame) CV book. Thanks, thsant!
[0905.3369] Learning Nonlinear Dynamic Models
We present a novel approach for learning nonlinear dynamic models, which leads to a new set of tools capable of solving problems that are otherwise difficult. We provide theory showing this new approach is consistent for models with long range structure, and apply the approach to motion capture and high-dimensional video data, yielding results superior to standard alternatives.
Procrastineering - Project blog for Johnny Chung Lee: Project Natal
The 3D sensor itself is a pretty incredible piece of equipment providing detailed 3D information about the environment similar to very expensive laser range finding systems but at a tiny fraction of the cost. Depth cameras provide you with a point cloud of the surface of objects that is fairly insensitive to various lighting conditions allowing you to do things that are simply impossible with a normal camera.
Topics in High-Level Vision: Object and Scene Processing
This seminar, intended for graduate students and advanced undergraduates, will survey the state of the art in object recognition and scene interpretation. We shall discuss computational principles behind these cognitive functions and examine up-to-date behavioral data, neurobiological findings (including single-cell and imaging data), and computer models. The material will include, among other topics, the Bayesian framework for perception and generative methods for processing object and scene structure.
Clustering Billions of Images with Large Scale Nearest Neighbor Search
Image collections on this scale make performing even the most common and simple computer vision, image processing, and machine learning tasks non-trivial. An example is nearest neighbor search, which not only serves as a fundamental subproblem in many more sophisticated algorithms, but also has direct applications, such as image retrieval and image clustering. In this paper, we address the nearest neighbor problem as the first step towards scalable image processing. We describe a scalable version of an approximate nearest neighbor search algorithm and discuss how it can be used to find near duplicates among over a billion images.
-
Image collections on this scale make performing even the most common and simple computer vision, image processing, and machine learning tasks non-trivial. An example is nearest neighbor search, which not only serves as a fundamental subproblem in many more sophisticated algorithms, but also has direct applications, such as image retrieval and image clustering. In this paper, we address the nearest neighbor problem as the first step towards scalable image processing. We describe a scalable version of an approximate nearest neighbor search algorithm and discuss how it can be used to find near duplicates among over a billion images.
ImageNet
ImageNet is an image database organized according to the WordNet hierarchy (currently only the nouns), in which each node of the hierarchy is depicted by hundreds and thousands of images. Currently we have an average of over five hundred images per node. We hope ImageNet will become a useful resource for researchers, educators, students and all of you who share our passion for pictures.
Machine Learning (Theory) » Interesting Presentations at Snowbird
Yann LeCun convolutional networks on FPGAs; Image ontology
Xavier BRESSON - Code
A Fast Global Minimization Algorithm for Active Contour Models
based on the Split-Bregman Method, Matlab/C Code
-
A
Fast Global Minimization Algorithm for Active
Contour Models
based on the Split-Bregman Method, Matlab/C
Code -
A fast global minimization algorithm is developed to minimize a large
class of segmentation models called active contours. We believe that
the proposed theory and algorithm produce so far one of the most
efficient minimization methods for the active contour segmentation
problem. For example, the well-know cameraman picture, which size is
256x256, is segmented in less than 0.1 seconds. Besides, our
algorithm, while being easier to code, produces results slightly
faster than the popular and fast graph-cuts technique. Our algorithm
is also more accurate than graph-cuts because it uses isotropic
schemes to regularize the contour and is sub-pixel accurate. Besides,
the memory requirement is low. Finally, the reader can make fast its
own active contour model. We emphasized in the code the parts where
the reader can add his/her own model.
PyCV - A Computer Vision Package for Python Incorporating Fast Training of Face Detection
-
- Fast training and selection of Haar-like features for a weak classifier
[Pham2007b]. This is currently the world's fastest method for training a
face detector. It runs in just a few hours, while most existing methods run
in days or weeks. - Multi-exit Asymmetric Boosting [Pham2008]: a variant of AdaBoost that learns
a cascade more optimally than traditional cascade learning methods. - Asymmetric Online Boosting [Pham2007a]: a variant of AdaBoost that learns
incrementally using an asymmetric goal as the learning criterion.
PyCV is a package of C++ and Python modules implementing various algorithms
that are useful in computer vision, and augments the capabilities of OpenCV.
In particular, PyCV provides implementations for: - Fast training and selection of Haar-like features for a weak classifier
Selected Tags
Related Tags
Sponsored Links
Top Contributors
Groups interested in computer...
Diigo is about better ways to research, share and collaborate on information. Learn more »
Join Diigo