Cellular Neural Networks for object-oriented segmentation

被引：0

作者：

Grassi, Giuseppe ^{[1
]}

Vecchio, Pietro ^{[1
]}

机构：

[1] Univ Lecce, Dipartimento Ingn Innovaz, I-73100 Lecce, Italy

来源：

PRIME 2006: 2ND CONFERENCE ON PH.D. RESEARCH IN MICROELECTRONIC AND ELECTRONICS, PROCEEDINGS | 2006年

关键词：

D O I：

暂无

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

By exploiting the Cellular Neural Network paradigm, this paper present a new object-oriented segmentation algorithm that takes into account the hardware characteristics of the Cellular Neural Networks Universal Machine. In particular, by using a rigorous model of the image contours, this paper focuses on the edge extraction phase as well as on the performance evaluations. Simulation results, carried out for Stefan, Coast Guard, Car-phone and Football video sequences, show the effectiveness of the approach developed herein.

引用

页码：253 / +

页数：2

共 4 条

[1]

*AN COMP LTD, 2000, CSL CNN SOFTW LIB VE

[2] New object-oriented segmentation algorithm based on the CNN paradigm [J].

Grassi, G ;

Di Sciascio, E ;

Grieco, LA ;

Vecchio, P .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS, 2006, 53 (04) :259-263

[3] Object-oriented image analysis using the CNN universal machine: New analogic CNN algorithms for motion compensation, image synthesis, and consistency observation [J].

Grassi, G ;

Grieco, LA .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS, 2003, 50 (04) :488-499

[4]

Stoffels A, 1996, IEEE T CIRCUITS-I, V43, P948

← 1 →