基于免疫粒子群优化算法的影像纹理分类

粒子群优化算法是基于群智能的随机全局优化方法，它源于对鸟群简化社会系统的模拟。为了提高标准粒子群优化算法的收敛性能，将生物免疫系统的记忆能力和多样性引入标准粒子群优化算法，提出一种免疫粒子群优化算法。在提取纹理样本Laws纹理能量模板特征、小波特征等纹理特征的基础上，提出针对分类问题的粒子表达方法和群体寻优策略，实现了基于免疫粒子群算法的纹理分类。实验结果表明，与标准粒子群优化算法相比，免疫粒子群优化算法在获取训练样本类别中心时具有较好的收敛性能，并且基于该算法的影像纹理分类具有较高的分类精度。

Image Texture Classification Based on Immune Particle Swarm Optimization

Particle swarm optimization is a stochastic global optimization method based on swarm intelligence.It was developed through simulation of a simplified social system such as bird flocking.In order to improve the convergence performance of standard particle swarm optimization,immune particle swarm optimization is proposed by means of introducing memory ability and diversity of biologic immune system into standard particle swarm optimization in this paper.The particles in the swarm are constructed and swarm search strategies of immune particle swarm optimization are proposed in terms of the needs of the classification application after many texture features such as Laws texture energy template features and wavelet features are extracted from texture samples.Then the image texture classification algorithm based on immune particle swarm optimization is implemented to solve image texture classification problems.Compared with standard particle swarm optimization in the image texture classification experiment,immune particle swarm optimization has better convergence performance in training the image texture samples to get the centers of classification and the classification method based on it has higher classification accuracy.