MindX: Mixed Impulse Poisson-Gaussian DenoisingThis work aims at developing denoising algorithms for images corrupted by mixed impulse noise and Poisson-Gaussian noise.  Details here X-Ray Computed TomographyThis works aims at developing high quality X-ray CT Reconstruciton algorithms based on proximal operators.  Arabic Sentiment AnalysisThis work explores applying Sentiment Analysis techniques to the Arabic language, especially in the field of social media.  Street View Goes IndoorsThis work explores processing a set of unordered spherical panoramas of an indoor place by estimating their relative poses to extract a scaled map of the place suitable for indoor exploration and navigation.
 Details here Distributed Kd-Trees for Large Scale Image SearchThis work explores using Distributed Kd-Trees for implementing fast, accurate, and scalable large scale image search.
 Details here Compact Kd-Trees for Large Scale Image SearchThis work explores using Distributed Kd-Trees for implementing fast, accurate, and scalable large scale image search.
 Details here Large Scale Image Search Benchmark
This work performs a thorough benchmark of the two leading approaches for large
scale image search: Bag of Words (BoW) vs Full Representation (FR). It includes
methods such as: Inverted File, Min-Hash, Kd-Trees, Hierarchical K-Means,
Locality Sensitive Hashing (LSH), among others.
Details here Online Parameter Selection for Large Scale Image Search
This work explores using online learning for selecting the best parameters
of Bag of Words systems when searching large scale image collections.
Details here Automatic Discovery of Image Families
This work investigates the problem of how to automatically discover image families
in unorganized image collections. Image families are groups of images with significant
similarity. The problem has applications to content-based image search, automatic
visualization and organization of image collections, or computer vision research
datasets, among others.
 Details here Real time Lane Detection in Urban Streets
This project was part of Team Caltech,
Caltech's entry in the DARPA Urban Challenge
in November 2007. This project's main aim was to detect and localize lane lines in
urban streets, which will help Alice, Team Caltech's autonomous vehicle, find its way
in traffic.
 Details here Fast Face Detection
This project was done as a requirement for the
Computer Vision
class EE148 of Spring 2006. The project was mainly to provide an open source
Matlab implementation of a realtime face detection system developed by
François Fleuret.
Details here Face Recognition using SIFT Features
This project was part of the requirements of the
CNS/Bi/EE 186:
Vision: From Computational Theory to Neuronal Mechanisms class for Winter 2006.
It implemented a simple face recognition system in Matlab exploiting the
power of SIFT features to discriminate between faces of different individuals.
Details here Survey on Multi-Class ClassificationDescriptionThis project aimed at compiling a survey for the various techniques used for multi-class classification. This is an important problem, specially in computer vision, where we would like to recognize hundreds of different object categories. The survey report introduces the several techniques employed to solve this problem, with a discussion of their advantages and disadvantages.ReferencesMohamed Aly, Survey on Multi-Class Classification Methods. [pdf] |
Research
Subpages (12):
Arabic Sentiment Analysis
Automatic Discovery of Image Families
Compact Kd-Trees for Large Scale Image Search
Distributed Kd-Trees for Large Scale Image Search
Face Recognition using SIFT Features
Fast Face Detection
Large Scale Image Search Benchmark
MindX: Mixed Impulse Poisson-Gaussian Denoising
Online Parameter Selection for Large Scale Image Search
Real Time Lane Detection in Urban Streets
Street View Goes Indoors
X-Ray Computed Tomography
Comments
