Skills (16)
Research experience
-
Jan 2008–
Feb 2011Research: Griffith University
Griffith University · Queesland Micro- and nanotechnology centerAustralia · Brisbane
Education
-
Oct 2006–
Nov 2008Griffith University
Pattern Recognition, Circuits and Systems · Ph.D.Australia · Brisbane
Other
-
LanguagesEnglish
-
Scientific MembershipsIEEE
ACM -
Journal RefereesIEEE Transactions on Image Processing, IEEE Concurrency, IEEE Transaction SMC: B
Questions and Answers (16) View all
-
Answer added in Pattern Classification11 Machine Learning: Learning with categoric data and very few training examples?Search for one-sample problems and small sample problems.. Its a topic of interest to many people like me :) .. More than dimensionality reduction, pr... [more]
-
Answer added in Social Network Analysis22 What is the average length of a doctoral thesis?Anything, 10000 words would be more than enough, as far as contributions are clear, fair and progressive, for present and future use.
-
Answer added in Speech Processing11 How to carry out signals and systems labs effectively.Oh that is strange. I have been using both for research and teaching for several years, I did find it to be very different in its purpose and use. If ... [more]
-
Question asked in Social Engineering21 Is technological singularity near?It's often said that computing power and intelligence would exceed the collective intelligence of humans. Can computers form their own societies (with... [more]
-
Answer added in Speech Processing11 How to carry out signals and systems labs effectively.As far as making students learn the concepts effectively - is concerned - labview software is good. I think its important to start with fundamentals s... [more]
Publications (33) View all
-
Article: One-sample Face Recognition with Local Similarity Decisions
Internaitonal Journal of Applied Pattern Recognition. 01/2013; 1(1). -
Article: Biologically Inspired Features Used For Robust Phoneme Recognition
[show abstract] [hide abstract]
ABSTRACT: Formants are regarded as the basic building blocks of vowels; however, they are very rarely used as features for difficult automatic speech recognition tasks. Formant based research is generally focused on formant extraction, because of the assumption that a better formant extraction method is the only manner to increase the effectiveness of formants. We challenge this assumption by investigating a different use of formants following their extraction. By using the same principles of combining formants as observed in speech perception studies, we create features that show good recognition performance under noisy testing conditions. Improved recognition performance with the proposed formant features is demonstrated by comparing to Melfrequency cepstrum coefficients and perceptual linear predictive coding features on a hidden Markov model based automatic speech recognition system.Int.J. Machine Intel. and Sen. Signal Processing. 01/2013; 1. -
Chapter: Machine Intelligence Using Hierarchical Memory Networks
01/2013; -
Article: Resistive Threshold Logic
IEEE Transactions on Very Large Scale Integration (VLSI) Systems 01/2013; · 1.22 Impact Factor -
Article: Examplers based image fusion features for face recognition
[show abstract] [hide abstract]
ABSTRACT: Examplers of a face are formed from multiple gallery images of a person and are used in the process of classification of a test image. We incorporate such examplers in forming a biologically inspired local binary decisions on similarity based face recognition method. As opposed to single model approaches such as face averages the exampler based approach results in higher recognition accu- racies and stability. Using multiple training samples per person, the method shows the following recognition accuracies: 99.0% on AR, 99.5% on FERET, 99.5% on ORL, 99.3% on EYALE, 100.0% on YALE and 100.0% on CALTECH face databases. In addition to face recognition, the method also detects the natural variability in the face images which can find application in automatic tagging of face images.01/2012;
