Találati lista | Tudóstér

001-es BibID:	BIBFORM073509
Első szerző:	Tiba Attila (informatikus, matematikus)
Cím:	Efficient Texture Regularity Estimation for Second Order Statistical Descriptors / Attila Tiba, Harangi Balázs, Hajdu András
Dátum:	2017
Megjegyzések:	Co-occurrence matrices as sources of secondorder statistical descriptors are commonly used intexture classification tasks. To generate such a matrix, we need a position vector to check possible intensityfrequencies in its endpoints. In this paper, we proposean efficient algorithm to locate such position vectorsaccording which the pattern of the texture repeats andthus, the descriptors (Haralick features) derived fromthe co-occurrence matrix are capable to characterize theregularity of the pattern. The essence of our approachis to look for vectors that span well-approximating gridsdefined by reference points obtained by quantizing theinput image. To extract such grids we use the LLLalgorithm, which has a polynomial running time. Thus,we have a much more efficient solution than e.g. a bruteforce based search. Our results show that the proposedapproach is capable to suggest position vectors for anefficient co-occurrence matrix based texture analysis.
ISBN:	978-1-5090-4011-7
Tárgyszavak:	Műszaki tudományok Informatikai tudományok előadáskivonat co-occurrence matrix texture analyses regular texture descriptors LLL algorithm
Megjelenés:	Proceedings of the 10th International Image and Signal Processing and Analysis (ISPA) / Ed. Stanislav Kovačič, Sven Lončarić, Matej Kristan, Vitomir Štruc, Mladen Vučić. - p. 90-94. -
További szerzők:	Harangi Balázs (1986-) (programtervező matematikus) Hajdu András (1973-) (matematikus, informatikus)
Pályázati támogatás:	EFOP-3.6.2-16-2017-00015 EFOP GINOP-2.1.1-15-2015-00376 GINOP VKSZ 14-1-2015-0072, SCOPIA: Egyéb
Internet cím:	Szerző által megadott URL DOI Intézményi repozitóriumban (DEA) tárolt változat
Borító:
Saját polcon: