Ústav teorie informace a automatizace

Jste zde

Bibliografie

Conference Paper (international conference)

Medical Image Segmentation Using Cooccurrence Matrix Based Texture Features Calculated on Weighted Region

Tesař Ludvík, Smutek D., Shimizu A., Kobatake H.

: Advances in Computer Science and Technology . IASTED international conference 2007 /3./, p. 1-7

: IASTED International Conference on Advances in Computer Science and Technology 2007 /3./, (Phuket, TH, 02.04.2007-04.04.2007)

: CEZ:AV0Z10750506

: 1ET101050403, GA AV ČR, 1M0572, GA MŠk

: medical image analysis, bioinformatics, pattern recognition

(eng): An improvement of texture based 2D or 3D co-occurrence based image segmentation method is proposed, aimed at medical image analysis. The co-occurerrence matrix is calculated so that each cooccurrence is weighted by the function of distance from the original pixel of interest.

(cze): Navrhuje se vylepšení ko-okurenční metody pro 2D nebo 3D segmentaci medicínských obrázků. Ko-okurenční matice se počítá tak, že každá ko-okurence se váží vzdáleností od bodu, pro který se matice počítá.

: IN

07.01.2019 - 08:39