Digit recognition using trispectral features
Data(s) |
1997
|
---|---|
Resumo |
Features derived from the trispectra of DFT magnitude slices are used for multi-font digit recognition. These features are insensitive to translation, rotation, or scaling of the input. They are also robust to noise. Classification accuracy tests were conducted on a common data base of 256× 256 pixel bilevel images of digits in 9 fonts. Randomly rotated and translated noisy versions were used for training and testing. The results indicate that the trispectral features are better than moment invariants and affine moment invariants. They achieve a classification accuracy of 95% compared to about 81% for Hu's (1962) moment invariants and 39% for the Flusser and Suk (1994) affine moment invariants on the same data in the presence of 1% impulse noise using a 1-NN classifier. For comparison, a multilayer perceptron with no normalization for rotations and translations yields 34% accuracy on 16× 16 pixel low-pass filtered and decimated versions of the same data. |
Formato |
application/pdf |
Identificador | |
Publicador |
IEEE |
Relação |
http://eprints.qut.edu.au/45577/1/00595439_ICASSP97.pdf DOI:10.1109/ICASSP.1997.595439 Chandran, Vinod, Slomka, S., Gollogly, M., & Elgar, S. (1997) Digit recognition using trispectral features. In Acoustics, Speech, and Signal Processing, 1997. ICASSP-97., 1997 IEEE International Conference on, IEEE, Los Alamitos, California, pp. 3065-3068. |
Direitos |
Copyright 1997 IEEE 2011 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. |
Fonte |
Faculty of Built Environment and Engineering; School of Engineering Systems |
Palavras-Chave | #character recognition #discrete Fourier transforms #feature extraction #image classification #motion estimation #spectral analysis #DFT magnitude slices #bilevel images #classification accuracy tests #digit recognition #multi-font digit recognition #noise #randomly rotated noisy versions #testing #training #translated noisy versions #trispectral features |
Tipo |
Conference Paper |