When the size of an image such as a picture or a painting is beyond the scope of a camera, it is difficult to take the whole picture which is a high resolution image all at once. In this case, each part of the image is taken by a camera one by one. A part of the image is an image patch. Using image patches, the whole picture is reproduced. This method is called image mosaicing. However the method has disadvantages for the reproduction of a high resolution image as follows. 1. When there are regions that do not have features or intensity gradients, it is hard to reproduce the original image because they are used to register each part of the image. 2. The higher the number of image patches, the more the image distortion is cumulated because errors on the borders between image patches are added. To solve these problems, the layered image mosaicing method is proposed. In this paper, the concept, implementation and an experiment are described. The experiment showed that the method was effective for image mosaicing.
[1]
Roger Y. Tsai,et al.
A versatile camera calibration technique for high-accuracy 3D machine vision metrology using off-the-shelf TV cameras and lenses
,
1987,
IEEE J. Robotics Autom..
[2]
Richard Szeliski,et al.
Video mosaics for virtual environments
,
1996,
IEEE Computer Graphics and Applications.
[3]
Steve Mann,et al.
Virtual bellows: constructing high quality stills from video
,
1994,
Proceedings of 1st International Conference on Image Processing.
[4]
Rachid Deriche,et al.
Using geometric corners to build a 2D mosaic from a set of images
,
1997,
Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.