Ignas Kukenys

Computer Science Ph.D. student, under the supervision of Brendan McCane and Geoff Wyvill.

Research

My main research topic is Face Detection with Support Vector Machines. The things I've worked on include SVM bootstrapping, SVM approximation and classifier cascades, approximate SVM training, training on large data sets and data set augmentation.

Publications

• I. Kukenys, B. McCane, T. Neumegen. Training Support Vector Machines on Large Sets of Image Data. In Asian Conference on Computer Vision, 2009. ACCV 2009. 9th International Conference, 2009.
• I. Kukenys and B. McCane. Classifier Cascades for Support Vector Machines. In Image and Vision Computing New Zealand, 2008. IVCNZ 2008. 23rd International Conference, 2008.
• I. Kukenys and B. McCane. Support Vector Machines for Human Face Detection. In NZCSRSC 2008: Proceedings of the New Zealand Computer Science Research Student Conference, 2008.

Other things

• Approximate SVM Training: How to train an SVM with 1 million examples?, poster for ACCV 2009 (1MB PDF)
• Million Dollar Machine, presentation for a Graphics Lab Meeting 2009 (180KB PDF)
• Cascades Of Support Vector Machines, presentation for Otago Postgraduate Conference 2008 (1.1MB PDF)
• Classifier Cascades For Support Vector Machines, poster for IVCNZ08 (1.2MB PDF)
• Human Face Detection With Support Vector Machines, poster for NZCSRSC08 (2.8MB PDF)
• Tiny SVM v2: a Java Applet demonstrating the SVM learning algorithm with 2D points.