Compressive sensing fast classification for handwritten digital images

doi:10.37188/OPE.20212907.1709

CIOMP OpenIR

	Compressive sensing fast classification for handwritten digital images
	X. S.-M; W. S.-J; C. L and F. R.-P
	2021
发表期刊	Guangxue Jingmi Gongcheng/Optics and Precision Engineering
ISSN	1004924X
卷号	29 期号:7 页码:1709-1719
摘要	To reduce the training calculation time and optimal training times of a neural network model and ensure high classification accuracy of handwritten digital images, compressive sensing technology was introduced, and a fast classification algorithm of handwritten digital images based on compressive sensing and a single-hidden layer feedforward network (Compressive sensing and single-hidden layer feedforward network, CS-SHLNet) was proposed. First, a Gaussian random matrix is used to obtain a linear measurement of the handwritten digital image with sparseness, and the high-dimensional image signal is projected to the low-dimensional space to obtain the measurement value. Second, using the error backpropagation (BP) algorithm, the weights of the neural network are continuously adjusted to establish a single-hidden layer feedforward network model suitable for the measurement values, which are embedded into the neural network for image feature extraction. Finally, a single-hidden layer feedforward network model is used to classify handwritten digits, and the model is quantitatively evaluated by the time-consuming training calculations, the optimal training times, and the classification accuracy. Experimental results show that-in contrast to using a single-hidden layer neural network and deep learning for high-dimensional image signal classification of MNIST handwritten numeral datasets-through the CS technology, the Gaussian random matrix linear measurement number, i.e., M=235, is first used to obtain the image measurement value; then, the single-hidden layer feedforward network is used for image classification. The training calculation time of the network model is reduced to 13.05 s, the best training times are reduced by a factor of three, and the classification accuracy is 97.5%. The compressive sensing linear measurement in the algorithm can effectively reduce the computation time of the training and the optimal training times of the neural network model for handwritten digital datasets and the classification accuracy can be ensured. 2021, Science Press. All right reserved.
DOI	10.37188/OPE.20212907.1709
URL	查看原文
收录类别	EI
引用统计
文献类型	期刊论文
条目标识符	http://ir.ciomp.ac.cn/handle/181722/65109
专题	中国科学院长春光学精密机械与物理研究所
推荐引用方式 GB/T 7714	X. S.-M,W. S.-J,C. L and F. R.-P. Compressive sensing fast classification for handwritten digital images[J]. Guangxue Jingmi Gongcheng/Optics and Precision Engineering,2021,29(7):1709-1719.
APA	X. S.-M,W. S.-J,&C. L and F. R.-P.(2021).Compressive sensing fast classification for handwritten digital images.Guangxue Jingmi Gongcheng/Optics and Precision Engineering,29(7),1709-1719.
MLA	X. S.-M,et al."Compressive sensing fast classification for handwritten digital images".Guangxue Jingmi Gongcheng/Optics and Precision Engineering 29.7(2021):1709-1719.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Compressive sensing （2375KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览下载