Handwritten digit classification using higher order singular value decomposition

Authors:
Berkant Savas;Lars Eldén
Affiliations:
Department of Mathematics, Linköping University, 581 83 Linköping, Sweden;Department of Mathematics, Linköping University, 581 83 Linköping, Sweden
Venue:
Pattern Recognition
Year:
2007

Citing 7
Cited 19

Matrix computations (3rd ed.)

Matrix computations (3rd ed.)
Optical character recognition

Optical character recognition
A Multilinear Singular Value Decomposition

SIAM Journal on Matrix Analysis and Applications
On the Best Rank-1 and Rank-(R1,R2,. . .,RN) Approximation of Higher-Order Tensors

SIAM Journal on Matrix Analysis and Applications
Multilinear Analysis of Image Ensembles: TensorFaces

ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part I
Pattern Classification (2nd Edition)

Pattern Classification (2nd Edition)
Modeling the manifolds of images of handwritten digits

IEEE Transactions on Neural Networks

Handwritten Digit Classification Based on Alpha-Beta Associative Model

CIARP '08 Proceedings of the 13th Iberoamerican congress on Pattern Recognition: Progress in Pattern Recognition, Image Analysis and Applications
An Approach to Searching for Two-Dimensional Cellular Automata for Recognition of Handwritten Digits

MICAI '08 Proceedings of the 7th Mexican International Conference on Artificial Intelligence: Advances in Artificial Intelligence
Multi modal semantic indexing for image retrieval

Proceedings of the ACM International Conference on Image and Video Retrieval
Kernel-based learning from infinite dimensional 2-way tensors

ICANN'10 Proceedings of the 20th international conference on Artificial neural networks: Part II
A new implementation of common matrix approach using third-order tensors for face recognition

Expert Systems with Applications: An International Journal
PARAFAC algorithms for large-scale problems

Neurocomputing
Visual system for drivers' eye recognition

HAIS'11 Proceedings of the 6th international conference on Hybrid artificial intelligent systems - Volume Part I
Classification of clinical gene-sample-time microarray expression data via tensor decomposition methods

CIBB'10 Proceedings of the 7th international conference on Computational intelligence methods for bioinformatics and biostatistics
Object recognition with the HOSVD of the multi-model space-variant pattern tensors

CAIP'11 Proceedings of the 14th international conference on Computer analysis of images and patterns - Volume Part I
Hybrid clustering of multi-view data via Tucker-2 model and its application

Scientometrics
Uni-orthogonal nonnegative tucker decomposition for supervised image classification

ICIAP'11 Proceedings of the 16th international conference on Image analysis and processing: Part I
Hybrid clustering of multiple information sources via HOSVD

ISNN'10 Proceedings of the 7th international conference on Advances in Neural Networks - Volume Part II
Ensemble of tensor classifiers based on the higher-order singular value decomposition

HAIS'12 Proceedings of the 7th international conference on Hybrid Artificial Intelligent Systems - Volume Part II
Higher-order SVD analysis for crowd density estimation

Computer Vision and Image Understanding
A New Truncation Strategy for the Higher-Order Singular Value Decomposition

SIAM Journal on Scientific Computing
Perturbation Theory and Optimality Conditions for the Best Multilinear Rank Approximation of a Tensor

SIAM Journal on Matrix Analysis and Applications
Feature selection from high-order tensorial data via sparse decomposition

Pattern Recognition Letters
Embedding of the extended euclidean distance into pattern recognition with higher-order singular value decomposition of prototype tensors

CISIM'12 Proceedings of the 11th IFIP TC 8 international conference on Computer Information Systems and Industrial Management
Hybrid computer vision system for drivers' eye recognition and fatigue monitoring

Neurocomputing

Quantified Score

Hi-index	0.01

Visualization

Abstract

In this paper we present two algorithms for handwritten digit classification based on the higher order singular value decomposition (HOSVD). The first algorithm uses HOSVD for construction of the class models and achieves classification results with error rate lower than 6%. The second algorithm uses the HOSVD for tensor approximation simultaneously in two modes. Classification results for the second algorithm are almost down at 5% even though the approximation reduces the original training data with more than 98% before the construction of the class models. The actual classification in the test phase for both algorithms is conducted by solving a series least squares problems. Considering computational amount for the test presented the second algorithm is twice as efficient as the first one.