Abstract--- This paper presents an overview of feature extraction methods for off-line recognition of segmented (isolated) characters. Selection of a feature extraction method is probably the single most important factor in achieving high recognition performance in character recognition systems. Different feature extraction methods are designed for different representations of the characters, such as solid binary characters, character contours, skeletons (thinned characters), or gray level subimages of each individual character. The feature extraction methods are discussed in terms of invariance properties, reconstructability, and expected distortions and variability of the characters. The problem of choosing the appropriate feature extraction method for a given application is also discussed. When a few promising feature extraction methods have been identified, they need to be evaluated experimentally to find the best method for the given application. Feature extraction Optical character recognition Character representation Invariance Reconstructability
|
2961
|
Pattern Classification and Scene Analysis
– Duba, Hart
- 1973
|
|
1943
|
Snakes: Active contour models
– Kass, Witkin, et al.
- 1987
|
|
1745
|
Eigenfaces for Recognition
– Turk, Pentland
- 1991
|
|
1664
|
Introduction to statistical pattern recognition, 2nd ed
– Fukunaga
- 1990
|
|
677
|
Computer Vision
– Ballard, Brown
- 1982
|
|
491
|
Visual pattern recognition by moment invariants
– Hu
- 1962
|
|
456
|
Pattern Recognition: A Statistical Approach
– Devijver, Kittler
- 1982
|
|
232
|
Methods of combining multiple classifiers and their applications to handwriting recognition
– Xu, Krzyzak, et al.
- 1992
|
|
169
|
Syntactic Pattern Recognition and Applications
– Fu
- 1982
|
|
134
|
Shape discrimination using Fourier descriptors
– Persoon, Fu
- 1977
|
|
98
|
Invariant image recognition by zernike moments
– Khotanzad, Hong
- 1990
|
|
87
|
Thinning methodologies: A comprehensive survey
– Lam, Lee, et al.
- 1992
|
|
77
|
Historical review of OCR research and development
– Mori, Suen, et al.
- 1992
|
|
74
|
Goal-Directed Evaluation of Binarization Methods
– Trier, Jain
- 1995
|
|
67
|
Recognizing Planar Objects Using Invariant Image Features
– Reiss
- 1993
|
|
62
|
Dimensionality and sample size considerations in pattern recognition practice
– Jain, Chandrasekaran
|
|
59
|
Computer recognition of unconstrained handwritten numerals
– Suen, Nadal, et al.
- 1992
|
|
55
|
Elliptic Fourier Features of a Closed Contour , Computer Gr aphics and Image Processing 18
– Kuhl
- 1982
|
|
54
|
A Fast Parallel Algorithm for Thinning Digital Patterns
– Zhang, Suen
- 1984
|
|
41
|
A Bayesian approach to dynamic contours through stochastic sampling and simulated annealing
– Storvik
- 1994
|
|
39
|
Evaluation of Binarization Methods for Document Images
– Trier, Taxt
- 1995
|
|
39
|
Automatic recognition of handprinted characters – the state of the art
– Suen, Berthod, et al.
- 1980
|
|
34
|
Omnidocument Technologies
– Bokser
- 1992
|
|
32
|
Handwritten numerical recognition based on multiple algorithms
– Kimura, Shridhar
- 1991
|
|
28
|
An overview of character recognition methodologies
– Mantas
- 1986
|
|
25
|
At the frontiers of OCR
– Nagy
- 1992
|
|
25
|
The revised fundamental theorem of moment invariants
– Reiss
- 1991
|
|
21
|
A Review of Segmentation and Contextual Analysis Techniques for Text Recognition
– Elliman, Lancaster
- 1990
|
|
20
|
Partial shape recognition using dynamic programming
– Gorman, Mitchell, et al.
- 1988
|
|
18
|
A.P.: Character recognition – a review
– Govindan, Shivaprasad
- 1990
|
|
16
|
Building a new generation of handwriting recognition systems
– Suen, Legault, et al.
- 1993
|
|
11
|
Recognition of handwritten digits using template and model matching. Pattern Recognition
– Gader, Forester, et al.
- 1991
|
|
8
|
Performance evaluation of skeletonizing algorithms for document image processing
– Lee, Lam, et al.
- 1991
|
|
8
|
Quantitative performance evaluation of thinning algorithms under noisy conditions
– Jaisimha, Haralick, et al.
- 1994
|
|
5
|
Character segmentation techniques for handwritten text --- a survey
– Dunn, Wang
- 1992
|
|
3
|
Multidimensional rotations in feature selection
– Andrews
- 1971
|
|
2
|
Pattern Recognition Techniques
– Ullmann
- 1973
|
|
2
|
Handwritten numeral recognition with multiple features and multistage classifiers
– Cao, Ahmadi, et al.
- 1994
|
|
2
|
OCR from poor quality images by deformation of elastic templates
– Bimbo, Santini, et al.
- 1994
|
|
1
|
Desaultes, "Application of shape analysis to mammographic calcifications
– Shen, Rangayyan, et al.
- 1994
|
