Study on Acyclic Lateral Inhibition Network Model and Its Application for Image Processing

被引：2

作者：

Fu, Hongwei ^{[1
]}

Li, Dongguang ^{[1
]}

Guan, Renhang ^{[1
]}

机构：

[1] Beijing Inst Technol, Sch Aerosp Sci & Engn, Beijing 100081, Peoples R China

来源：

2008 INTERNATIONAL SYMPOSIUM ON INTELLIGENT INFORMATION TECHNOLOGY APPLICATION, VOL III, PROCEEDINGS | 2008年

关键词：

D O I：

10.1109/IITA.2008.554

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

For overcoming the problems of algorithms in image edge detection, like distortion and shift of object's edge, easily losing the object detail information and higher demand for object detection in the modem war, this essay analyses the feasibility of lateral inhibition model in object detection, based on lateral inhibition theory, an acyclic lateral inhibition network model (ALINM) with biology vision information processing mechanism was introduced. This model has the merits of rapid calculating, easily real time operation, etc. Besides the correctness of ALINM is confirmed by two input cells, its transfer function is deduced. An algorithm of image edge detection based on this model is established finally, and simulative experiment with different parameters proves that this algorithm can preserve the farthest detail information of objects. It provides a useful method based on biology vision for object detection under difficult imaging conditions.

引用

页码：301 / 305

页数：5