Projects

e-glue

This program glues images to get a bigger and better image from a sequence of small images. Its use low resolution images taken from mobile devices. The images doesn't have to be perfectly aligned because the software will align them. The current version is ... [More] http://code.google.com/p/e-glue/source/browse/#svn/tags/egluesh_0.1.0. Please, if you want to help us, send an e-mail to e-glue at openmobo.org. Visit the homepage at http://e-glue.openmobo.org/. [Less]

pysift

A lightweight python wrapper for sift++ (a C++ implementation of the Scale-Invariant Feature Transform) which takes an image and returns a list of SIFT descriptors. Note: The SIFT algorithm has a patent as described below (from http://vision.ucla.edu/~vedaldi/code/siftpp/siftpp.html) This ... [More] software embodies a method for which the following patent has been issued: "Method and apparatus for identifying scale invariant features in an image and use of same for locating an object in an image," David G. Lowe, US Patent 6,711,293 (March 23, 2004). Provisional application filed March 8, 1999. Asignee: The University of British Columbia. The original sift++ code can be found at http://vision.ucla.edu/~vedaldi/code/siftpp/siftpp.html. Note it is only free for research use (due to the patent). [Less]

neural-object

This software uses the SIFT algorithm, combined with a neural network, to do image processing and image recognition.

opensurf1

Library Last Updated 18/03/2010All downloads are now hosted on my projects siteIf you're looking for the latest build of the OpenSURF library, you'll find it at Chris Evans Development. You'll also find papers on the OpenSURF library along with links to applications which use the ... [More] library. OpenSURF is a clean, unintrusive SURF feature extraction library written in C++ with OpenCV. The OpenSURF library was originally written in Visual Studio 2005, although a linux compatible makefile has been contributed and is available in the SVN directory. Should you wish to contribute to the project please email your Google Code id and I will arrange SVN access. If you have any comments/questions/suggestions please feel free to Contact Me [Less]

sift-coprojeto

Co-projeto Software Hardware

javasurf

Java implementation on speeded up robust features SURF. SURF (Speeded Up Robust Features) is a robust image descriptor, first presented by Herbert Bay et al. in 2006, that can be used in computer vision tasks like object recognition or 3D reconstruction. It is partly inspired by the SIFT ... [More] descriptor. The standard version of SURF is several times faster than SIFT and claimed by its authors to be more robust against different image transformations than SIFT. SURF is based on sums of 2D Haar wavelet responses and makes an efficient use of integral images. As basic image features it uses a Haar wavelet approximation of the determinant of Hessian blob detector. More about surf on http://en.wikipedia.org/wiki/SURF Currenty this project is refactored version of http://processingsurf.al [Less]

ndfinder

The major objective of the project is: Given an image, to find its duplicated and near-duplicated images in an indexed image library. The core algorithm will written in C++, and provides a dll and some other APIs in different languages. The project is powered by SIFT an LSH (E2LSH).

sunman

for faster and more robust

VLFeat

The VLFeat open source library implements popular computer vision algorithms including SIFT, MSER, k-means, hierarchical k-means, agglomerative information bottleneck, and quick shift. It is written in C for efficiency and compatibility, with interfaces in MATLAB for ease of use, and detailed documentation throughout.

Multimodal

Multimodal medical image classification written in C++ and Java using Hadoop, Mahout and Weka.