CVPR14 Program
A selection of interesting papers from this years CVPR conference

May 30, 2014

This list includes a selection of papers from this year's Compter Visoin and Pattern Recognition conference. The conference has a lot of papers and many of them are also very good.

  • Face Alignment at 3000 FPS via Regressing Local Binary Features
  • Socially-aware Large-scale Crowd Forecasting
  • Human Action Recognition by Representing 3D Skeletons as Points in a Lie Group
  • Real-time Hand Tracking on Depth Images
  • Make3D: Learning 3D Scene Structure from a Single Still Image
  • Deep Learning with Hierarchical Convolutional Factor Analysis

Here is a link to the whole proramme:

Starting object recognition
General object detection using Histogram of Oriented Gradients and SVMs

May 25, 2014

This past month I've looked at object recognition. Initially I was interested in people detection which led me to look at a particular feature extraction method called Histogram of Oriented Gradients (HOGs), but then it became clear that the HOG descriptor can find general shapes and is robust against varying lighting and object orientation.

I use HOG descriptors and Support Vector Machines (SVMs) to detect people in standard datasets. The image below shows the result of processing one sample frame.

Voice Control using an Android client and Spotify
Using voice to play, pause, play next and previous songs using speech

Mar 02, 2014
Sunday hacking - Rotate desktop using an accelerometer
This screen automatically rotates when you flip it

Oct 23, 2013

This is an idea by a friend --- to use an accelerometer to rotate the desktop.

Speech recognition
Implementing feature extraction for human speech

Sep 11, 2013

After concluding my work with face detection (see below) I naturally started to research speech recognition with the goal to create a single word recognition system for home.

For a very long time I struggled with Hidden Markov Models (HMMs) used in many recognitioning systems today However, lately I found out that HMMs are possibly overkill for the single word recognitioning system I was aiming for and I implemented a technique called Dynamic Time Warping which so far works well.

Below is a plot of various stages in converting the speech input (top left) to feature vectors (bottom right). The feature extraction is performed using Mel-Cepstral coefficients which extract vocal properties from the log-power spectra of the speech signal.

The figure shows recorded speech (top left) which is filtered to extract the interesting samples (bottom left). This filtered data is used in the spectral analysis to compute Mel-Cepstram coefficients (top right) which are used as weights to the inverse transformation back to time domain (bottom right).

Face detection and recognition
Implementing the Eigenface method

Jul 29, 2012

If you have never tried OpenCV I would recommend it for any type of image processing. Earlier this year I modified the Haar-detectioning sample script to do some cool effects. Now this summer, I have implemented my own face recognition software based on the eigenfaces technique. This software is part of a larger project that I will put some time into this fall. The picture below shows a sample application I built around the recognition software. It shows portraits of a camera feed and lets the user select and save the portrait which is immediately loaded into the recognitioning software.

The library works well but there are immediate improvements that I will have to complete before I continue to build on this code.

Poster presenter at Nvidia GTC 2012
GPU conference in San Jose, USA

Apr 18, 2012
The same poster send to GTC Asia (below) has also been accepted to GTC in San Jose, USA.
Poster presenter at Nvidia GTC 2011
GPU conference in Beijing, Chaina

Dec 14, 2011
We performed work jointly with High Performance Consulting during Master studies which was accepted to Nvidias GPU Technology Conference. This work benchmark perofmance and power consumption for three HPEC radar benchmarks including, pattern recognition and genetic algorithms.
Since 2012, this site has presented work on artificial intelligence and machine learning with applications to biometrics.
Histogram of Oriented Gradients extracts features from objects based on the orientation of gradients. These features can be used to find any object in an image
This website is hosted by a Pandaboard. The goal is to run this energy efficient machine only on solar power. More updates on this project soon!
Sentient performs speech recognition for single- and multi word voice control. We use Sentient as a backend for many other projects