Title :
Clustering of visual pattern keys by cascading decomposition
Author :
Melnyk, Roman ; Tushnytskyy, Ruslan
Author_Institution :
Software Dept., Lviv Polytech. Nat. Univ., Lviv, Ukraine
Abstract :
The clustering algorithm for storage and searching of visual patterns keys is considered. To reduce algorithmic complexity of the application to formulate the visual patterns clusters the cascade decomposition approach for keys and clusters is proposed. Some results with quality characteristics of decomposition depending from partitioning parameters are presented.
Keywords :
image recognition; pattern clustering; algorithmic complexity; cascading decomposition; image recognition; integrated areas; partitioning parameters; pattern clustering; visual pattern keys; Cluster; fingerprint; integrated areas; rectangles; rolling-up algorithm; visual pattern;
Conference_Titel :
Modern Problems of Radio Engineering, Telecommunications and Computer Science, 2008 Proceedings of International Conference on
Conference_Location :
Lviv-Slavsko
Print_ISBN :
978-966-553-678-9
