Two-Stage Image Classification Method Based on Three-Way Decisions

被引：0
|
作者：
Chen C. [1 ,2 ]
Zhang H. [1 ,2 ]
Cai K. [1 ,2 ]
Miao D. [1 ,2 ]
机构：
[1] College of Electronics and Information Engineering, Tongji University, Shanghai
[2] The Key Laboratory of Embedded System and Service Computing, Ministry of Education, Tongji University, Shanghai
来源：
Moshi Shibie yu Rengong Zhineng/Pattern Recognition and Artificial Intelligence | 2021年 / 34卷 / 08期
基金：
中国国家自然科学基金;
关键词：
Convolutional Neural Network; Deep Learning; Image Classification; Shadowed Sets; Three-Way Decisions;
D O I：
10.16451/j.cnki.issn1003-6059.202108010
中图分类号：
学科分类号：
摘要：
A single model cannot handle the uncertainty in prediction results effectively, and therefore, the shadowed sets theory is introduced into image classification from the perspective of three-way decisions and a two-stage image classification method is designed. Firstly, samples are classified by convolutional neural networks to obtain the membership matrix. Then, a sample partitioning algorithm based on shadowed sets is employed to process the membership matrix and consequently the uncertain part of the classification results, the uncertain domain, for delayed decision making is obtained. Finally, feature fusion technique is utilized and SVM is regarded as a classifier for secondary classification to reduce the uncertainty of the classification results and improve the classification accuracy. Experiments on CIFAR-10 and Caltech 101 datasets validate the effectiveness of the proposed method. © 2021, Science Press. All right reserved.
引用
下载
收藏
页码：768 / 776
页数：8
相关论文
共 35 条
  • [1] OJALA T, PIETIKAINEN M, HARWOOD D., A Comparative Study of Texture Measures with Classification Based on Featured Distributions, Pattern Recognition, 29, 1, pp. 51-59, (1996)
  • [2] OJALA T, PIETIKAINEN M, MAENPAA T., Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns, IEEE Transactions on Pattern Analysis and Machine Inte-lligence, 24, 7, pp. 971-987, (2002)
  • [3] LOWE D G., Distinctive Image Features from Scale-Invariant Keypoints, International Journal of Computer Vision, 60, 2, pp. 91-110, (2004)
  • [4] LOWE D G., Object Recognition from Local Scale-Invariant Features, Proc of the 7th IEEE International Conference on Computer Vision, II, pp. 1150-1157, (1999)
  • [5] DALAL N, TRIGGS B., Histograms of Oriented Gradients for Human Detection, Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, I, pp. 886-893, (2005)
  • [6] COVER T, HART P E., Nearest Neighbor Pattern Classification, IEEE Transactions on Information Theory, 13, 1, pp. 21-27, (1967)
  • [7] CORTES C, VAPNIK V., Support-Vector Networks, Machine Lear-ning, 20, pp. 273-297, (1995)
  • [8] BREIMAN L., Random Forests, Machine Learning, 45, pp. 5-32, (2001)
  • [9] KRIZHEVSKY A, SUTSKEVER I, HINTON G E., ImageNet Classification with Deep Convolutional Neural Networks, Communications of the ACM, 60, 6, pp. 84-90, (2017)
  • [10] SIMONYAN K, ZISSERMAN A., Very Deep Convolutional Networks for Large-Scale Image Recognition
1234