论文部分内容阅读
激光图像分类是大规模激光图像检索的基础,传统激光图像分类方法存在速度慢、正确率低的缺陷。为了改善激光图像分类效果,针对传统方法存在的缺陷,提出了粗糙集与神经网络的激光图像分类和识别方法。首先提取激光图像的特征,采用粗糙集约简特征,然后采用神经网络建立激光图像的分类器,实现激光图像的识别,最后采用激光图像数据对分类效果进行验证,结果表明,本文方法获得比传统方法的激光图像分类结果,具有更优的实际应用价值。
Laser image classification is the basis of large-scale laser image retrieval. The traditional laser image classification method has the defects of slow speed and low accuracy. In order to improve the effect of laser image classification, aiming at the defects of traditional methods, a method of laser image classification and recognition based on rough sets and neural networks is proposed. Firstly, the features of the laser image are extracted, the rough set is used to reduce the feature, then the neural network is used to build the classifier of the laser image to recognize the laser image. Finally, the laser image data is used to verify the classification results. The results show that the proposed method achieves better performance than traditional methods The result of laser image classification has better practical application value.