سال انتشار: ۱۳۸۹
محل انتشار: ششمین کنفرانس ماشین بینایی و پردازش تصویر
تعداد صفحات: ۵
Shahin Sohrabi – Iran University of Science and Technology
Ali Asghar Behshti Shirazi – Iran University of Science and Technology
Siavash Ghalamifard – Sahand University of Technology
The key performances of the star pattern recognition algorithms are the identification efficiency and the time consumed. In the past decades, much effort has been made in database search methods and lots of them are made out. To reduce the computation database search time a novel technique using star magnitudes is proposed. Also, we propose a novel, smart and fast star identification algorithm by using this accurate and fast searching method. The simulation results based on the Desktop Universes images show that the proposed star identification and database search algorithm can achieve both high accuracy and fast recognition. The database search and star features extraction time is O(n). In addition to, since the quality of star images play an important role in improving accuracy of star pattern recognition algorithm, therefore for image pre-processing we propose a fuzzy edge detection technique. This method highly affects noise cancellation, star features extraction, database production and matching algorithm.