Computing and Information Systems - Research Publications

Search Results

Now showing 1 - 1 of 1

Edge gradient correction of distorted images: a differential chain rule approach

Islam, Mr Muhammad ; Kitchen, Dr Les ( 2007-11)

Many camera lenses, particularly low-cost or wideanglelenses, can cause significant image distortion. Thismeans that measurements made on such images will be incorrect.A traditional approach to dealing with this problemis to digitally unwarp the image to correct the distortion,and then to apply computer vision processing to the corrected image. However, this is a relatively expensive operation, and can introduce additional interpolation errors. We propose instead to apply processing directly to the distorted image, modifying the algorithm to account for the distortion during processing.In this paper we focus on the particular classic problemof gradient-based extraction of straight edges. We propose amodification of the Burns [4] line extractor that works on adistorted image by correcting the gradients on the fly usingthe chain rule, and correcting the pixel positions during the line-fitting stage. Experimental results on both real and synthetic images show that our gradient-correction technique speeds up processing over traditional unwarping approach, while retaining similar accuracy.