Classification of Repetitive Patterns Using Symmetry Group Prototypes

摘要: We present a novel computational framework for automatic classification method by symmetries, periodic images applied to content based image retrieval. The existing methods have several drawbacks because of the use heuristics. These shown low values when exhibit imperfections due fabrication or hand made process. Also, there is no way give some computation goodness-of-fit. propose obtain an parameter estimation symmetry analysis. Thus, redefined as distances prototypes set defined classes. Our experimental results improves state art in wallpaper methods.