obscuracam.png
ObscuraCam
I have continued my interest in visual privacy protection by contributing and consulting on the
ObascuraCam open source project. My main contribution has been to develop the Jpeg-Redaction-Library to provide compressed-domain manipulation and redaction of JPEG images and removal/editing of EXIF/IPTC metadata for the purposes of privacy protection.
voicesearch.jpg
Google OCR
I have been contributing to an Optical Character Recognition
project withing Google research.
voicesearch.jpg
Google Search by Voice
Search the web, get directions, dictate an email, all by voice.
pets.jpg
Video Surveillance Tracking
The tracking system used in the "PeopleVision" project and the IBM
Smart Surveillance Solution.
privacytarget.png
Privacy Protection in Video Surveillance
Automatic video understanding technologies can help protect privacy in
video surveillance systems. This project seeks to hide
privacy-intrusive information in surveillance video. I edited a book
and co-edited a journal special issue on the subject.
heatmap.jpg
Vision systems for Retail applications
Retail is a major application area of automatic video
analytics. I organised a
special session at AVSS 2007 on the topic. This project
created a system for returns fraud prevention for a national chain.
homographytracks.png
Automatic calibration for active camera control
A multi-camera system to automatically track pedestrians with an active camera. The
calibration is learned automatically from observing people walking
through the scene.
particlefilter.png
3D Speaker tracking
Several 3D person tracking algorithms were developed as part of the EU
CHIL (Computers in the Human Interaction Loop) project, using 2D
blob trackers, face trackers and this particle filter tracker.
articedgefit.png
3d Articulated body tracking
A system to track the person's limbs with a 3D graphical model using 2
or more cameras. Running in real time and with moving cameras to cover a wide
area.
lips.jpg
Audio-visual speech recognition
Facial feature locations from the face tracker (below) were used to generate visual features in the first audio-visual, large vocabulary continuous speech recognition system. The system was also used to do speech activity detection for "visual push to talk"
facialfeatures.png
Face recognition
The video face detection and tracking algorithms (below) were extended to a mutliplatform face recognition system that worked on live video, still images or broadcast video.
skintone.png
Face detection and facial feature location
A system for real-time face detection in video that also localized the facial features for recognition, expression understanding and speech recognition.
fpclassifydecisiontree.png
Fingerprint classification
Fingerprint
classification using a combination of methods (including HMM and
decision trees) that gave the best classification results published at
the time on the standard NIST database.
distortedfingerprint.png
Fingerprint distortion removal
A novel way of removing the distortion in fingerprints that improved recognition performance.
durationmodel.png
Online handwriting recognition
Handwriting recognition for tablet computers. The system became part
of the IBM CrossPad/ThinkScribe and TransNote products.
offlinehandwriting.png
Off-line handwriting recognition
PhD Thesis on "Off-line handwriting recognition using recurrent neural
networks" - a neural-network / HMM hybrid recognition system. Incorporating
forward-backward retraining of the networks, large vocabulary language modelling and
out-of-vocabulary word modelling.
LIMSIModel.png
Continuous speech recognition with Hidden Markov Models
Conducted at LIMSI, at the Universite de Paris XI, as part of a European project.