...
首页> 外文期刊>Computer and Information Science >A New Process of Color Images Recognition by Using ART-1 Neural Network
【24h】

A New Process of Color Images Recognition by Using ART-1 Neural Network

机译:利用ART-1神经网络进行彩色图像识别的新方法

获取原文

摘要

In this paper ART1 neural network algorithm is used for recognition of color images which speeds up the process of Image processing and its recognition process. But, generally Adaptive Resonance Theory-1(ART-1) network is used only for processing binary digits, but in this paper it may also be used for image recognition. The given fact limits the loss of information as a result, two different colors in which inside one original image can be represented as a same value of binary color during recognition. These mistakes are overcome by our image recognition method here.This method is very attractive because of its low computational overhead, improved performance comparatively than other networks with less number of neurons. Experimental results are given finally which are encouraging in this paper.
机译:本文将ART1神经网络算法用于彩色图像的识别,从而加快了图像处理及其识别过程。但是,通常,自适应共振理论-1(ART-1)网络仅用于处理二进制数字,但是在本文中,它也可以用于图像识别。给定的事实限制了信息的丢失,结果是两种不同的颜色,其中一个原始图像内部可以在识别期间表示为相同的二进制颜色值。这些错误可以通过我们的图像识别方法来克服。该方法非常有吸引力,因为它的计算开销较低,与其他神经元数量较少的网络相比,性能得到了改善。最后给出了实验结果,这在本文中是令人鼓舞的。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号