Interactions between Number Theory and Image Analysis

In this project, we have investigated the fusion of surface data obtained by two different surface recovery methods. In particular, we have fused the depth maps obtained by shape from contours and local surface orientation maps obtained by photometric stereo. It has been found that the surface obtained by fusing orientation and depth data is able to yield more precision when compared with the surfaces obtained by either type of data alone. 1 The University of Auckland, Tamaki Campus, Centre for Image Technology and Robotics, Computer Vision Unit, Auckland, New Zealand 2 Centre for Machine Perception, Faculty of Engineering, Czech Technical University, Czech Republic Integration of photometric stereo and shape from occluding contours by fusing orientation and depth data Yen Chen and Radim Šára Centre for Image Technology and Robotics, Tamaki Campus, University of Auckland, New Zealand [email protected] Centre for Machine Perception Faculty of Electrical Engineering, Czech Technical University, Czech Republic [email protected] 1 Abstract In this project, we have investigated the fusion of surface data obtained by two different surface recovery methods. In particular, we have fused the depth maps obtained by shape from contours and local surface orientation maps obtained by photometric stereo. It has been found that the surface obtained by fusing orientation and depth data is able to yield more precision when compared with the surfaces obtained by either type of data alone.