摘要
提出了一种新的基于目标边界的傅立叶描述子 ,并用于表示二维目标特征和作为神经网络的输入 .该描述子具有对目标的大小、旋转、位移不变等特性 .实验中对各种姿态不同型号的飞机进行识别 。
We describe a neural networks based recognition scheme for 2\|D objects. The novel boundary based fourier descriptors for 2\|D objects are taken as the features and they form the input to the neural network. A multilayered perceptron architecture is used for the classification and the back\|propagation learning algorithm is used for the network learning. The scheme is invariant to translation, rotation, and scale changes to the object. Taking different kinds of planes with varied postures as the input data set, we show that the presented scheme gives very high recognition accuracy and fault\|tolerance. The novel boundary based fourier descriptors and simulation results are discussed in detail.
关键词
描述子
BP网络
目标识别
descriptors
BP neural network
recognition
