Slow Feature Discriminant Analysis and its application on handwritten digit recognition

Yaping Huang; Jiali Zhao; Mei Tian; Qi Zou; Siwei Luo

doi:10.1109/IJCNN.2009.5178596

Neural Networks, IEEE - INNS - ENNS International Joint Conference on

Slow Feature Discriminant Analysis and its application on handwritten digit recognition

Year: 2009, Pages: 1294-1297

DOI Bookmark: 10.1109/IJCNN.2009.5178596

Authors

Yaping Huang, Department of Computer Engineering, The Beijing Jiaotong University, China
Jiali Zhao, Department of Computer Engineering, The Beijing Jiaotong University, China
Mei Tian, Department of Computer Engineering, The Beijing Jiaotong University, China
Qi Zou, Department of Computer Engineering, The Beijing Jiaotong University, China
Siwei Luo, Department of Computer Engineering, The Beijing Jiaotong University, China

Abstract

Slow Feature Analysis (SFA) is an unsupervised algorithm by extracting the slowly varying features from time series and has been used to pattern recognition successfully. Based on SFA, this paper develops a new algorithm, Slow Feature Discriminant Analysis (SFDA), which can maximize the temporal variation of between-class time series, and minimize the temporal variation of within-class time series simultaneously. Due to adoption of discrimination power, the performance on pattern recognition is improved compared to SFA. The experiments results on MNIST digit handwritten database also show that the proposed algorithm is in particular attractive.

Like what you’re reading?

Already a member?

Get this article FREE with a new membership!

ReD-SFA: Relation Discovery Based Slow Feature Analysis for Trajectory Clustering
2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
DL-SFA: Deeply-Learned Slow Feature Analysis for Action Recognition
2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Slow Feature Analysis for Multi-Camera Activity Understanding
2013 International Conference on Virtual Reality and Visualization (ICVRV)
Heuristic Evaluation of Expansions for Non-linear Hierarchical Slow Feature Analysis
Machine Learning and Applications, Fourth International Conference on
Learning Slow Features for Behaviour Analysis
2013 IEEE International Conference on Computer Vision (ICCV)
Slow Feature Analysis for Human Action Recognition
IEEE Transactions on Pattern Analysis & Machine Intelligence
Slow Feature Preprocessing in Deep Neural Networks for Wearable Sensor-Based Locomotion Recognition
2022 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events (PerCom Workshops)
Deep Network-based Slow Feature Analysis for Human Fall Detection
2022 International Conference on Computational Modelling, Simulation and Optimization (ICCMSO)
Unsupervised Learning of Metric Representations with Slow Features from Omnidirectional Views
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
Slow Feature Analysis Based Quality Prediction for Slow Time-Varying Batch Processes
2020 7th International Conference on Information Science and Control Engineering (ICISCE)

Slow Feature Discriminant Analysis and its application on handwritten digit recognition

Authors

Abstract

Related Articles