期刊文献+

基于卷积神经网络的图像识别研究 被引量:1

Research on image recognition based on convolution neural network
下载PDF
导出
摘要 为降低图像识别误识率,文章采用卷积神经网络结构对图像进行识别研究。首先,对输入图像进行初始化;然后,初始化后的图像经卷积层与该层中卷积核进行卷积,对图像进行特征提取,提取的图像特征经过池化层进行特征压缩,得到图像最主要、最具代表性的点;最后,通过全连接层对特征进行综合,多次迭代,层层压缩,进而对图像进行识别,输出所识别图像。与原始算法相比,该网络构造可以提高图像识别准确性,大大降低误识率。实验结果表明,利用该网络模型识别图像误识率低至16.19%。 In order to reduce the false recognition rate of image recognition, this paper uses convolution neural network structure to identify the image. First, the input image is initialized; then, the initialized layer of the image is convoluted with the convolution kernel in the layer, and the feature extraction is carried out. The extracted image features are compressed by the pool layer to get the most representative and most representative feature points of the image. The features of the extracted layer are integrated through the full link layer, iterated repeatedly, compressed layer by layer, and then the image is identified and the identified image is output. Compared with the original algorithm, the network structure can improve the accuracy of image recognition and greatly reduce the false recognition rate. The experimental results show that the false recognition rate of the image recognition system using this network model is as low as 16.19%.
作者 谢慧芳 刘艺航 王梓 王迎港 Xie Huifang;Liu Yihang;Wang Zi;Wang Yinggang(Henan Normal University,Xinxiang 453007,China)
机构地区 河南师范大学
出处 《无线互联科技》 2018年第14期23-24,共2页 Wireless Internet Technology
关键词 卷积神经网络 卷积核 特征提取 特征压缩 convolution neural network convolution kernel feature extraction feature compression
  • 相关文献

参考文献4

二级参考文献69

  • 1孙鹏程,王帮田,洪文芳,王其中.SF_6/N_2混合气体绝缘特性的实验研究[J].中国电力,2012,45(12):71-75. 被引量:15
  • 2Feldkamp L A, Davis L C, Kress J W. Practical cone-beam algorithm. Journal of the Optical Society of America A, 1984, 1(6): 612-619.
  • 3Kak A C, Slanet M. Principles of Computerized Tomographic Imaging. New York: IEEE Press, 1988.
  • 4Lange K, Carson R. EM reconstruction algorithms for emission and transmission tomography. Journal of ComputerAssisted Tomography, 1984, 8(2): 306-316.
  • 5Beckman F J, Kamphuis C. Ordered subset reconstruction for x-ray CT. Physics in Medicine and Biology, 2001, 46: 1835-1844.
  • 6Elbakri I A, Fessler J A. Statistical image reconstruction for polyenergetic x-ray computed tomography. IEEE Transactions on Medical Imaging, 2002, 21(2): 89-99.
  • 7Chueh H S, Tsai W K, Chang C C, et al. An iterative reconstruction for poly-energetic X-ray computed tomography. Medical Imaging and lnformatics, 2008, 4987: 44-50.
  • 8Kole J S, Beekman F J. Evaluation of accelerated iterative x-ray CT image reconstruction using floating point graphics hardware. Physics in Medicine and Biology, 2006, 51: 875-889.
  • 9Weinlich A, Keck B, Scherl H, et al. Comparison of high-speed ray casting on GPU using CUDA and openGL. In: Proceedings of the First International Workshop on New Frontiers in High-Performance and Hardware-Aware Computing. Lake Como, Italy, 2008.
  • 10Ollinger J M. Maximum-likelihood reconstruction of transmission images in emission computed tomography via the EM algorithm. IEEE Transactions on Image Processing, 1994, 13(1): 89-101.

共引文献17

同被引文献7

引证文献1

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部