Title :
Advanced algorithms for pattern identification
Author :
Vladislav, Skorpil ; Jiri, Stastny
Author_Institution :
Brno Univ. of Technol., Brno
Abstract :
Three advanced algorithms for pattern identification are compared in this paper. They are for identification with the aid of the momentum, identification with the aid of syntactic analysis and identification with the aid of neural network algorithm with back-propagation. Pattern identification consists in sorting objects into classes. Class is a subset of objects whose elements have common features from the classification standpoint. Object has a physical character, which in computer vision is most frequently taken to mean a part of segmented image.
Keywords :
backpropagation; image classification; image segmentation; neural nets; back-propagation; computer vision; image classification; image segmentation; neural network algorithm; object classification; pattern identification; syntactic analysis; syntactic identification; Algorithm design and analysis; Computer vision; Image analysis; Image generation; Image segmentation; Neural networks; Object recognition; Pattern analysis; Pattern recognition; Shape;
Conference_Titel :
Signal Processing, 2008. ICSP 2008. 9th International Conference on
Conference_Location :
Beijing
Print_ISBN :
978-1-4244-2178-7
Electronic_ISBN :
978-1-4244-2179-4
DOI :
10.1109/ICOSP.2008.4697460
