Prasad Gabbur

determination of the number of clusters.<br><br> Addressing these issues, I have worked on implementing a variant of Competitive Expectation Maximization (CEM) algorithm. Semantic evaluation of computer vision algorithms using word prediction performance Large databases of digital images that come with words associated with the images help to learn relationships among visual features of image regions and words. This can be used to predict words for new images automatically (auto- annotation).<br><br> It has applications in content-based image indexing and retrieval. I have worked on identifying and evaluating visual features, segmentation algorithms and color constancy algorithms using word prediction performance. Modifications to Normalized Cuts segmentation algorithm As part of my Master 9s thesis, I worked on modifying the Normalized Cuts segmentation algorithm to improve its grouping performance on images.<br><br> Further, comparison of the original and modified versions of the Normalized Cuts algorithm was done using word prediction tool. Human face detection and tracking in color image sequences As part of my undergraduate thesis, I worked in a group of two to develop an algorithm to detect and track human face(s) from color images/video. This was performed using statistical skin color modeling and connected component operators.<br><br> PUBLICATIONS cMultimodal probabilistic generative models for time-course gene expression data and Gene Ontology (GO) tags, d Prasad Gabbur and Kobus Barnard, Bioinformatics ( Oxford Journals) , to be submitted. "A fast connected components labeling algorithm for real-time pupil detection," Prasad Gabbur, Hong Hua, and Kobus Barnard, Machine Vision and Applications , January 2009. "Preserving the aesthetics during non-fixed aspect ratio scaling of the digital border," Hui Chao, Prasad Gabbur, and Anthony Wiley, ACM Symposium on Document Engineering , pp.<br><br> 144-146, 2007. "Cross modal disambiguation," Kobus Barnard, Keiji Yanai, Matthew Johnson, and Prasad Gabbur, in Toward Category- Level Object Recognition, Jean Ponce, Martial Hebert, Cordelia Schmid, eds., Springer-Verlag LNCS Vol. 4170, pp.<br><br> 225-244, 2006. "Evaluation Strategies for Image Understanding and Retrieval," Keiji Yanai, Nikhil V. Shirahatti, Prasad Gabbur and Kobus Barnard, Proc.<br><br> of ACM Multimedia Workshop on Multimedia Information Retrieval (MIR) , Singapore, November, 2005 (Invited paper). Prasad Gabbur 819 W Simmons Rd, #2, Tucson, AZ 85705 Ph. (520) 247 6726 Email: pgabbur@email.arizona.edu URL: http://www.ece.arizona.edu/~pgsangam cColor and Color Constancy in a Translation Model for Object Recognition, d Kobus Barnard, Prasad Gabbur, IS&T/SID 11 th Color Imaging Conference , pp.<br><br> 364-369, 2003. cThe effects of segmentation and feature choice in a translation model of object recognition, d Kobus Barnard, Pinar Duygulu, Raghavendra Guru, Prasad Gabbur, David Forsyth, IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) , Vol.<br><br> II, pp. 675-682, 2003. cHuman Face Detection and Tracking using Skin Color Modeling and Connected Component Operators, d Prem Kuchi, Prasad Gabbur, P.<br><br> Subbanna Bhat, Sumam David, IETE Jl. of Research , Vol. 38, No.<br><br> 3&4, pp. 289-293, May-Aug 2002. AWARDS / MERITS Graduate College Fellowship, University of Arizona, Fall 2001.<br><br> 3 rd rank to the University in my undergraduate degree (2 nd in a class of 75). EXPERIENCE University of Arizona Research Associate Spring & Fall 2003, Spring 2005 - Present Working on microarray data analysis. Worked on computer vision based eye-gaze tracking for fovea contingent displays.<br><br> Worked on image segmentation and visual features for auto-annotation using joint image-word modeling. Hewlett Packard Laboratories Research Associate Intern Summer 2006 Worked with Dr. Hui Chao on automatic content extraction and layout change in multilayer PSD images.<br><br> Developed a real-time algorithm to do connected components labeling to aid in the process of automatic content extraction. IntelliVision Technologies Corp., San Jose, CA Software Engineer Summer & Fall 2004 Worked on a motion detection algorithm in video for surveillance and security applications. Evaluated performances of different color spaces (RGB, HSL, CIE L*a*b* and YCbCr) in dealing with the effects of small illumination changes and weak shadows on motion detection.<br><br> Developed DSP algorithms for a people counting system based on a planar scan infrared sensor. Eyematic Interfaces Inc., Los Angeles, CA Intern Summer 2002 Worked on using synthetic images for representing faces under varying illumination conditions for a face detection system. Rendered a database of synthetic face images simulating different illuminations using 3D Studio Max.<br><br> University of Arizona Teaching Assistant Fall 2001, Spring & Fall 2002 C Programming for Engineering Applications Digital Signal Processing Indian Institute of Science, Bangalore, India Young Engineering Research Fellow Fall 2000 Research on developing a computational method for human face detection and tracking in color image sequences. GRADUATE LEVEL COURSES Random Processes for Engineering Applications Computer Vision Computer Graphics Linear Algebra Information Theory Stochastic Processes Fundamentals of Statistical Machine Learning Advanced Digital Signal Processing Computer Aided Logic Design Digital Image Processing Numerical Analysis Linear Systems Theory COMPUTER SKILLS Languages: C, C++, HTML, Perl. Packages: OpenGL, MATLAB.<br><br> Hardware Description Language: VHDL. Operating Systems: GNU/LINUX, MS Windows. REFERENCES Available upon request.<br><br>

less