Offline handwritten numerical recognition using orthogonal Gaussian mixture model

IEEE International Conference on Image Processing

Volumn 1, Issue , 2001, Pages 1126-1129

  Zhang, R ^a   Ding, X ^a  

^a TSINGHUA UNIVERSITY   (China)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS; APPROXIMATION THEORY; CORRELATION METHODS; DATA STRUCTURES; DATABASE SYSTEMS; EIGENVALUES AND EIGENFUNCTIONS; FEATURE EXTRACTION; MATHEMATICAL MODELS; MATHEMATICAL TRANSFORMATIONS; MATRIX ALGEBRA; TEXT PROCESSING; VECTOR QUANTIZATION;

COVARIANCE MATRIX; FEATURE VECTORS; GAUSSIAN MIXTURE MODEL; HANDWRITTEN NUMERAL RECOGNITION; OFFLINE NUMERAL RECOGNITION;

CHARACTER RECOGNITION;

EID: 0035163746     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (7)

1. Handwritten numerical recognition based on multiple algorithms
2. Robust text-independent speaker identification using Gaussian mixture speaker models
3. Statistical pattern recognition: A review
4. Feature extraction methods for character recognition-a survey
5. On the use of orthogonal GMM in speaker recognition
6. Maximum likelihood from incomplete data via the EM algorithm