摘要
由于军事背景下战场上不同目标的相似度极高以及复杂情况下的分类识别率不高,传统视觉特征的分类精度已不能满足要求。针对含有特定军事目标的大规模图像分类问题,构造了一种新的基于主成分分析(principal components analysis,PCA)白化的卷积神经网络结构,有效地降低了数据间的相关性,加强了学习能力,提高了目标分类的准确率。利用大规模的军事图像数据集对该模型进行了识别精度评估,实验表明,与基于视觉特征的词袋模型以及经典的卷积神经网络分类算法相比,该算法对于军事目标的分类精度有明显提高。
The classification accuracy of the traditional visual features can not meet the requirements in the application of modem military affairs due to the extremely high similarity of the different objects in the battlefield and low recognition rate in complex conditions. This paper presented a new architecture of the convolutional neural network （CNN） based on PCA whitening for solving the classification problem of large-scale images which contained some specific military objects. It efficiently eliminated the relativity of sample data, enhanced the learning ability and improved the accuracy of the object recognition. It tested and evaluated the new CNN model with the large-scale data from military images and compared with the traditional methods. The experiment results show that the algorithm has higher recognition rate on military object recognition.
出处
《计算机应用研究》
CSCD
北大核心
2017年第11期3518-3520,共3页
Application Research of Computers
基金
国家自然科学基金创新研究群体资助项目(61321002)
国家自然科学基金重大国际合作项目(61120106010)
国家教育部长江学者创新团队资助项目(IRT1208)
关键词
军事图像分类
深度学习
卷积神经网络
主成分分析白化
随机池化
military image classification
deep learning
convolutional neural network
PCA whitening
stochastic-pooling
