Composite morphological functions for DT-CNNs

Autor: Ter Brugge, MH, Nijhuis, JAG, Spaanenburg, L, Tetzlaff, R
Jazyk: angličtina
Rok vydání: 2002
Zdroj: CELLULAR NEURAL NETWORKS AND THEIR APPLICATIONS, 587-594
STARTPAGE=587;ENDPAGE=594;TITLE=CELLULAR NEURAL NETWORKS AND THEIR APPLICATIONS
Popis: Mathematical morphology is a powerful means to specify image manipulations; DT-CNN is the fast realization. The attractive combination has been sufficiently shown for simple problems but tends to fail in efficiency for more complex ones. The paper introduces a Complement and Argument Swap (CAS) equivalence that allows to solve an image processing problem through a small library of representative efficient designs.
Databáze: OpenAIRE