Projector Correction Approach for Unknown Geometry Surface

-Recently, portable LCD projectors have become increasingly popular for various usages. However a careful aligning to the projection surface or a flat screen are necessary for getting a good projection effect. If a projector can display an undistorted image on an unknown geometry surface, more and more applications can be expected. In this paper, we present a new new approach allowing a projector to display an undistorted image on an unknown geometry surface. To realize it, a single camera is used to capture the viewer’s perspective of the projection surface. There is no explicit camera and projector calibration needed in the approach. The procedure establishes the mapping from camera image to projector image by a well trained neural network (NN). After the mapping has been establised, a transform converter table is constructed from the output of NN. With the transform converter table (TCT), one can display an image corrected in real-time for the point of view of an observer, which takes into account his position, the surface distortion, and the projector position and orienttion. With using of NN, we do not need to carry out all image pixels for establishing the mapping. The mapping can be obtained correctly, if enough teaching points can be provided. The simulation results show that our approach is effective for correcting distortion caused by continuous projective surface and practical enough for most projector presentation. Key-Words:-Projector-camera system, Projective mapping, Distortion correction, Neural network, Computer Graphics, Keystone