Imtiaz Ahmed Taj
|Title||Ensemble Approach based on Score-Space Classification for Biometric Identification Applications|
Non-invasive personal identification based on biometrics is attracting significant attention due to vide range of security applications. Accuracy for such systems is still a challenge as the biometric images and features are not of desired quality due to constraints in the acquisition environment. For such system where accuracy is desired but is relatively difficult to achieve, ensemble approaches using different set of features and different types of base classifiers are viable as they enhance the overall accuracy a great deal. In this talk, score-space classification based ensembling technique is discussed and it is shown that this approach improves the overall accuracy of the system. Two case studies for 2D Face Recognition and 3D Face Recognition are demonstrated to show the concept and efficacy of the approach.
Dr. Imtiaz Ahmad Taj is currently Professor and Dean of Faculty of Engineering at the Capital University of Science and Technology (CUST) Islamabad. He completed his Bachelors in Electrical Engineering from University of Engineering and Technology (UET) Peshawar, in 1993. He did his Masters and PhD in Electronics and Information Engineering from Hokkaido University Japan, in 1998 and 2001, respectively. Dr Imtiaz is currently supervising the Vision and Pattern Recognition Systems (VisPRS) Research Group at CUST, and 7 PhD students have graduated under his supervision. His main areas of research interests include biometrics, vision based tracking and navigation, video processing and encoding, medical diagnostics based on ECG and EEG patterns analysis, and Medical image processing. He has authored or co-authored more than 50 international research papers including 30 papers in reputed journals. He also completed a number of funded R&D projects related to Biometrics, Vision based Navigation and Video Encoding.