摘要
针对高速旋转的相机拍摄图像产生的旋转运动模糊带来的目标分类较为困难的问题,本文主要研究手工特征与卷积神经网络(CNN)的结合,在网络结构底层赋予卷积神经网络不变性,提升网络在分类任务中的准确率。本文基于Gaussian-Hermite(GH)矩旋转运动模糊不变量(RMB_GHMI),通过计算卷积神经网络隐藏层特征图上的RMB GHMI来实现将旋转运动模糊不变性引入到卷积神经网络中,使网络本身具有一定的旋转运动模糊不变性,并使网络可从受到严重噪声干扰的旋转运动模糊的图像中直接进行目标分类。实验结果表明,在旋转运动模糊后的MNIST数据集上,相对于经典卷积神经网络,本文方法可以将图像分类准确率提升30%左右;在旋转运动模糊后的CIFAR-10数据集上,图像分类准确率可以提升4%~16%。
Aiming at the problem of object classification caused by the rotational motion blur of the image captured by the high-speed rotating camera,the combination of handcraft features and convolutional neural network(CNN)is studied to introduce the invariance into CNN and improve the accuracy of networks in classification tasks.In this paper,based on rotational motion blur Gaussian-Hermit(GH)moments invariants(RMB GHMI),calculating RMB GHMI on CNN feature map is used to introduce the invariance of rotational motion blur into CNN,which makes the network have certain invariance to rotational motion blur,and enables the network to classify objects directly from the image of rotational transform superimposed with rotational motion blur interfered by noises.Experimental results show that the proposed method can improve the classification accuracy of typical CNN on MNIST dataset image after rotational motion blur transforming by 30%,and improve the classification accuracy of typical CNN on CIFAR-10 dataset image after rotation motion blur transforming by 4%-16%.
作者
郭锐
郝优
许溟
贾丽
李华
GUO Rui;HAO You;XU Ming;JIA Li;LI Hua(Key Laboratory of Intelligent Information Processing,Institute of Computing Technology,Chinese Academy of Sciences,Beijing 100190;University of Chinese Academy of Sciences,Beijing 100049;The PLA 92728 Unit,Beijing 100036;The PLA 91977 Unit,Beijing 100036)
出处
《高技术通讯》
CAS
2022年第6期576-586,共11页
Chinese High Technology Letters
基金
国家重点研发计划(2019YFF0301801,2017YFB1002703)
国家重点基础研究发展计划(2015CB554507)
国家自然科学基金(61379082)资助项目。
