Pattern Recognition in Digital Images using Fractals

Abstract

Pattern recognition in digital images is a conjoint problem with application in remote sensing, electron microscopy, medical imaging and astrophysics, still no general solution which can be rivalled with the human cognitive system in which a pattern can be conceded subject to random positioning and scale. This research has stemmed in the design and implementation of a new algorithm for general pattern recognition based on the use of fractal image compression. This approach has for the first time allowed the pattern recognition problem to be solved in a way that is invariant of rotation and scale. It allows both ANNs and correlation to be used subject to appropriate pre-and post-processing techniques for digital image processing.