Character Rotation Absorption Using a Dynamic Neural Network Topology: Comparison With Invariant Features
Character Rotation Absorption Using a Dynamic Neural Network Topology: Comparison With Invariant Features
复制标题
使用动态神经网络拓扑的角色旋转吸收：与不变特征的比较
DOI：
10.5220/0002683500900097
复制
发表时间：
2004
期刊：
影响因子：
--
通讯作者：
A. Belaïd
中科院分区：
文献类型：
--
作者：
Christophe Choisy;H. Cecotti;A. Belaïd
本文讨论了多方位字符识别神经网络中的旋转吸收问题。经典的方法是基于几个旋转不变的功能。在这里，我们建议使用动态神经网络拓扑结构来吸收旋转现象。其基本思想是尽可能多地保留包含所有信息的图形信息。我们的建议是动态修改神经网络的架构，以考虑到所分析的模式的旋转变化。我们也使用了一个特定的拓扑结构，在网络内部进行极坐标变换。这种变换的目的是将旋转问题从一个问题转化为一个更容易处理的问题。这些建议被应用在一个合成的和一个真实的EDF 1多方向字符的基础上。与傅立叶和傅立叶-梅林不变量的比较。
This paper treats on rotation absorption in neural networks for multi-oriented character recognition. Classical approaches are based on several rotation invariant features. Here, we propose to use a dynamic neural network topology to absorb the rotation phenomenon. The basic idea is to preserve as most as possible the graphical information, that contains all the information. The proposal is to dynamically modify the neural network architecture, in order to take into account the rotation variation of the analysed pattern.We use too a specific topology that carry out a polar transformation inside the network. The interest of such a transformation is to transform the rotation problem from a problem to a problem, that is easier to treat. These proposals are applied on a synthetic and on a real EDF1 base of multi-oriented characters. A comparison is made with Fourier and Fourier-Mellin invariants.