A class of circularly-symmetric CNN spatial linear filters | Zendy

Radu Matei | Zendy; Liviu Goraș | Zendy

AI Assistant Blog Pricing

Home ZAIA Blog

Open Access

A class of circularly-symmetric CNN spatial linear filters

Author(s) -

Radu Matei,

Liviu Goraș

Publication year - 2006

Publication title -

facta universitatis - series electronics and energetics

Language(s) - English

Resource type - Journals

eISSN - 2217-5997

pISSN - 0353-3670

DOI - 10.2298/fuee0602299m

Subject(s) - grayscale , infinite impulse response , transformation (genetics) , computer science , class (philosophy) , linear filter , filter (signal processing) , simple (philosophy) , algorithm , spatial frequency , prototype filter , image (mathematics) , low pass filter , digital filter , topology (electrical circuits) , mathematics , artificial intelligence , computer vision , optics , physics , biochemistry , chemistry , philosophy , epistemology , combinatorics , gene

This paper proposes a simple and efficient method for designi ng a class of circularly-symmetric spatial linear filters implemente d on cellular neural networks. The design method relies on a so-called 1-D prototype filter, with desired character- istics and on a 1-D to 2-D spatial frequency transformation. Several design examples are given, for 2-D low-pass and band-pass filters (both of FIR and IIR type) with im- posed cut-off or peak frequency and a specified selectivity. Finally, simulation results are provided, on a real grayscale biomedical image.

The content you want is available to Zendy users.

Already have an account? Click here to sign in.

Having issues? You can contact us here

Accelerating Research