Mathematics model of feature combination classification was regarded as fitness function in order to develop pattern recognition robustness to noise, optimal selection of original flaw feature was realized with feature selection strategy based on genetic
Mathematics model of feature combination classification was regarded as fitness function in order to develop pattern recognition robustness to noise, optimal selection of original flaw feature was realized with feature selection strategy based on genetic
为提高缺陷模式识别对各种噪声及干扰的鲁棒性，提出以特征组合分类能力数学模型为适合度函数，设计基于遗传算法的特征选择策略，实现了对缺陷原始特征量的优化选择。