An image conversion algorithm from fish eye image to perspective image for human eyes

In this paper, we consider the omni-directional vision using equidistance projection fish eye lens. The partial domain of an original image in fish eye image is selected, and this is converted to a perspective image for human eyes based on a projection rule of fish eye lens so that it may become the same as a standard image which is obtained by central projection of common lens. However, since this conversion enlarges the original image spatially and is based on discrete data, crevice is generated in the converted image (sparse problem). To solve this problem, interpolation based on an intensity of the image is performed for the crevice in the converted image. This paper provides the experimental results of perspective image conversion for human eyes using the proposed conversion and interpolation methods for both gray-scale and color images, and the adequacy and improving point of the proposed techniques are discussed.