孙红辉, 王红霞, 田涛. 一种基于不变矩和BP网络的目标识别方法[J]. 微电子学与计算机, 2011, 28(3): 63-65,69.
引用本文: 孙红辉, 王红霞, 田涛. 一种基于不变矩和BP网络的目标识别方法[J]. 微电子学与计算机, 2011, 28(3): 63-65,69.
SUN Hong-hui, WANG Hong-xia, TIAN Tao. The Recognition Method of Objects Based on Moment Invariant and BP Neural Network[J]. Microelectronics & Computer, 2011, 28(3): 63-65,69.
Citation: SUN Hong-hui, WANG Hong-xia, TIAN Tao. The Recognition Method of Objects Based on Moment Invariant and BP Neural Network[J]. Microelectronics & Computer, 2011, 28(3): 63-65,69.

一种基于不变矩和BP网络的目标识别方法

The Recognition Method of Objects Based on Moment Invariant and BP Neural Network

  • 摘要: 为了有效地提高旋转、尺度变化目标的识别率,首先提取目标图像的不变矩,以此作为目标识别的特征向量,然后利用将附加动量项与自适应学习速率相结合的改进BP算法实现对目标的分类识别.字符图像仿真实验表明,这种针对旋转、尺度变化目标的识别方法是有效的,可行的.

     

    Abstract: In order to improve the recognition rate of rotation and scale changed objects, firstly the moment invariant of object images was extracted, which was taken as the characteristic vector, then improved BP algorithm that connects additional momentum with self-adaptive learning rate was used to classify and recognize the objects. The emulation experimental results of character images show the object recognition method of rotation and scale changed images is effective and feasible.

     

/

返回文章
返回