Method for retrieving the teaching image based on the improved convolutional neural network

被引：0
|
作者：
Liu D. [1 ,2 ]
Cui Y. [1 ]
Zhao Y. [1 ]
Song Y. [1 ]
Wang J. [1 ]
机构：
[1] School of Computer and Information Technology, Xinyang Normal Univ., Xinyang
[2] Henan Key Lab. of Analysis and Applications of Education Big Data, Xinyang Normal Univ., Xinyang
来源：
Xi'an Dianzi Keji Daxue Xuebao/Journal of Xidian University | 2019年 / 46卷 / 03期
关键词：
Convolution neural network; Feature extraction; Image retrieval; Principal component analysis;
D O I：
10.19665/j.issn1001-2400.2019.03.009
中图分类号：
学科分类号：
摘要：
Aiming at the loss of feature information caused by the convolution neural network in extracting image features and the reduction of high-dimensional image feature data, an image retrieval optimization scheme based on the improved convolution neural network is proposed. First, the image features are extracted through the convolutional layer of fusion, and a full connection layer is added between the convolutional layers of fusion to reduce the loss of image feature information. Then the PCA is used to effectively reduce the dimension of high-dimensional characteristic data and the high-dimensional feature vectors are mapped to the low-dimensional vector space. Finally, the cosine similarity method is used to match the similarity to achieve similar image retrieval. The proposed method is compared with classical methods such as LeNet-L and LeNet-5 in the performance of image retrieval. Experimental results show that the proposed retrieval method improves the recall rate and the average precision rate by at least 3%~27.3% compared with classical methods. © 2019, The Editorial Board of Journal of Xidian University. All right reserved.
引用
收藏
页码：52 / 58
页数：6
相关论文
共 11 条
  • [1] Bhute A.N., Meshram B.B., Text Based Approach for Indexing and Retrieval of Image and Video: a Review, Advances in Vision Computing: An International Journal, 1, 1, pp. 27-38, (2014)
  • [2] Wan J., Wang D., Hoi S.C.H., Et al., Deep Learning for Content-based Image Retrieval: a Comprehensive Study, Proceedings of the 2014 ACM International Conference on Multimedia, pp. 157-166, (2014)
  • [3] Demir B., Bruzzone L., A Novel Active Learning Method in Relevance Feedback for Content-based Remote Sensing Image Retrieval, IEEE Transactions on Geoscience and Remote Sensing, 53, 5, pp. 2323-2334, (2015)
  • [4] Xu Q., Li W., Zhan R., Et al., Improved Algorithm for SAR Target Recognition Based on the Convolutional Neural Network, Journal of Xidian University, 45, 5, pp. 177-183, (2018)
  • [5] Xiong C., Shan Y., Guo F., Image Retrieval Method Based on Image Principal Part Detection, Optics and Precision Engineering, 25, 3, pp. 792-798, (2017)
  • [6] He K.M., Zhang X.Y., Ren S.Q., Et al., Spatial Pyramid Pooling in Deep Convonlutional Networks for Visual Recogintion, IEEE Transcations on Pattern Anlysis and Machine Intelligence, 37, 9, pp. 1904-1916, (2015)
  • [7] Krizhevsky A., Sutskever I., Hinton G.E., ImageNet Classification with Deep Convolutional Neural Networks, Communications of the ACM, 60, 6, pp. 84-90, (2017)
  • [8] Zhou F., Jin L., Dong J., Review of Convolutional Neural Network, Chinese Journal of Computers, 40, 6, pp. 1229-1251, (2017)
  • [9] Jia Y., Shelhamer E., Donahue J., Et al., Caffe: Convolutional Architecture for Fast Feature Embedding, Proceedings of the 2014 ACM International Conference on Multimedia, pp. 675-678, (2014)
  • [10] Liu H., Li B., Lv X., Et al., Image Retrieval Based on Deep Convolutional Neural Network, Application Research of Computers, 34, 12, pp. 3816-3819, (2017)
12