Handwritten digit recognition: Benchmarking of state-of-the-art techniques.

DOI10.1016/S0031-3203(03)00085-2zbMath1054.68124MaRDI QIDQ1403787

Hiroshi Sako, Cheng-Lin Liu, Hiromichi Fujisawa, Kazuki Nakashima

Publication date: 4 September 2003

Published in: Pattern Recognition (Search for Journal in Brave)

zbMATH Keywords

Feature extractionPattern classificationDiscriminative learningHandwritten digit recognitionSupport vector classifier

Mathematics Subject Classification ID

Pattern recognition, speech recognition (68T10)

Related Items (22)

Optimal reduction of solutions for support vector machines ⋮ Class-specific feature polynomial classifier for pattern classification and its application to handwritten numeral recognition ⋮ Bias-variance decomposition in genetic programming ⋮ A genetic framework using contextual knowledge for segmentation and recognition of handwritten numeral strings ⋮ Fuzzy model based recognition of handwritten numerals ⋮ Improved support vector machine algorithm for heterogeneous data ⋮ Handwritten digit recognition: Benchmarking of state-of-the-art techniques. ⋮ A Modification of Solution Optimization in Support Vector Machine Simplification for Classification ⋮ Multiclass functional discriminant analysis and its application to gesture recognition ⋮ A method to make multiple hypotheses with high cumulative recognition rate using SVMs. ⋮ Handwritten digit recognition: Investigation of normalization and feature extraction techniques. ⋮ Distance-based margin support vector machine for classification ⋮ Recognition of degraded characters using dynamic Bayesian networks ⋮ A machine-learning approach for analyzing document layout structures with two reading orders ⋮ Side-information-induced reweighted sparse subspace clustering ⋮ Machine learning approach to automated quality identification of human induced pluripotent stem cell colony images ⋮ The probabilistic constraints in the support vector machine ⋮ Bilinear Lanczos components for fast dimensionality reduction and feature extraction ⋮ A new method for classifying random variables based on support vector machine ⋮ Text search for medieval manuscript images ⋮ A new benchmark on the recognition of handwritten Bangla and Farsi numeral characters ⋮ A multiple feature/resolution scheme to Arabic (Indian) numerals recognition using hidden Markov models

Uses Software

• MNIST
• CEDAR
• CENPARMI

Cites Work

• Unnamed Item
• Unnamed Item
• Handwritten digit recognition: Benchmarking of state-of-the-art techniques.
• Handwritten numeral recognition using gradient and curvature of gray scale image
• Robust vision-based features and classification schemes for off-line handwritten digit recognition
• Discriminative learning for minimum error classification (pattern recognition)
• Learning representations by back-propagating errors
• A Stochastic Approximation Method
• Evaluation of prototype learning algorithms for nearest-neighbor classifier in application to handwritten character recognition

This page was built for publication: Handwritten digit recognition: Benchmarking of state-of-the-art techniques.