Normalized neural networks for fast pattern detection

被引：0

作者：

El-Bakry, HM ^{[1
]}

Zhao, QF ^{[1
]}

机构：

[1] Univ Aizu, Aizu Wakamatsu 9658580, Japan

来源：

Proceedings of the International Joint Conference on Neural Networks (IJCNN), Vols 1-5 | 2005年

关键词：

fast pattern detection; neural networks; cross correlation; image normalization;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Neural networks have shown good results for detecting of a certain pattern in a given image. In our previous papers [1-6], a fast algorithm for ob ect/face detection was presented. Such algorithm was designed based on cross correlation in the frequency domain between the input image and the weights of neural networks. Our previous work also solved the problem of local subimage normalization in the frequency domain. In this paper, the effect of image normalization on the speed up ratio of pattern detection is presented. Simulation results show that local subimage normalization through weight normalization is faster than subimage normalization in the spatial domain. Moreover, the overall speed up ratio of the detection process is increased as the normalization of weights is done off line.

引用

页码：1889 / 1894

页数：6