Chaotic Attractor of the Image A New Image Feature

The probability of generating chaos can be substantially increased by cross-iteration between a class of special quadratic functions and random ones, and the result shows that it is a better method to construct chaotic system. The paper works on the chaotic characteristic of the dynamic system that constitutes of a quadratic surface mapping and an image function in a spatial unit area, the chaotic attractor is discovered as a new characteristic for image recognition. The chaotic attractor changes with the parameters and surface control points. In particular, the number of the attractor points but the distributive distinction can be changed by slightly adjusting the surface or image, and it has important significance for research on pattern recognition or vision mechanism. In addition, the experimental result shows that using the image chaotic attractor to recognize different human faces is measurable.