#### DMCA

## Wavelet-Based Feature Extraction for Handwritten Numerals

Citations: | 1 - 0 self |

### Citations

3468 | A theory for multiresolution signal decomposition: the wavelet representation”,
- Mallat
- 1989
(Show Context)
Citation Context .... Wavelet transforms have proved to be a powerful tool for image analysis, because of their capability to discriminate details at different resolutions. They have given good results in edge detection =-=[1]-=- and texture identification [2]. Discrete wavelet transforms (DWT) have been used to extract features for digit P. Foggia, C. Sansone, and M. Vento (Eds.): ICIAP 2009, LNCS 5716, pp. 374–383, 2009. c○... |

1468 | Gradient-based learning applied to document recognition.
- Lecun, Bottou, et al.
- 1998
(Show Context)
Citation Context ...st data set such that the results of different algorithms and preprocessing techniques can be fairly compared. MNIST is a modified version of NIST database and was originally set up by the AT&T group =-=[12]-=-. The normalized image data are available at webpage [13]. MNIST database contains 60,000 and 10,000 graylevel images (of size 28 × 28) for training and testing, respectively.Wavelet-Based Feature Ex... |

100 |
Computer recognition of unconstrained handwritten numerals
- Suen, Nadal, et al.
- 1992
(Show Context)
Citation Context ...atabase contains 60,000 and 10,000 graylevel images (of size 28 × 28) for training and testing, respectively.Wavelet-Based Feature Extraction for Handwritten Numerals 381 The CENPARMI digit database =-=[14]-=- was released by the Centre for Pattern Recognition and Machine Intelligence at Concordia University (CENPARMI), Canada. It contains unconstrained digits of binary pixels. In this database, 4,000 imag... |

90 |
The mnist database of handwritten digits; http://yann.lecun.com/exdb/mnist
- LeCun, Cortes
(Show Context)
Citation Context ... and preprocessing techniques can be fairly compared. MNIST is a modified version of NIST database and was originally set up by the AT&T group [12]. The normalized image data are available at webpage =-=[13]-=-. MNIST database contains 60,000 and 10,000 graylevel images (of size 28 × 28) for training and testing, respectively.Wavelet-Based Feature Extraction for Handwritten Numerals 381 The CENPARMI digit ... |

54 | Directional wavelets revisited: Cauchy wavelets and symmetry detection in patterns,
- Antoine, Murenzi, et al.
- 1999
(Show Context)
Citation Context ...the CWT is covariant under translations, because when applied to a translated image, it produces the translated CWT of the original image). This CWT has been applied for pattern recognition in images =-=[8]-=-, and has given satisfactory results for digit recognition [9]. We use it here to extract a shape-preserving smaller version of the digits and to build a complementary vector with information on orien... |

40 | Two-dimensional directional wavelets and the scale-angle representation
- Antoine, Murenzi
- 1996
(Show Context)
Citation Context ... frequential resolution. The 2D CWT has been extended by giving one principal orientation to the wavelet, via stretching one of its axes, and adding a rotational angle as a parameter to the transform =-=[6]-=-. It has translation, rotation and scale covariance [7] (the CWT is covariant under translations, because when applied to a translated image, it produces the translated CWT of the original image). Thi... |

34 |
Wavelet Descriptors for Multiresolution Recognition of Handprinted Characters
- Wunsch, Laine
- 1995
(Show Context)
Citation Context .... Sansone, and M. Vento (Eds.): ICIAP 2009, LNCS 5716, pp. 374–383, 2009. c○ Springer-Verlag Berlin Heidelberg 2009Wavelet-Based Feature Extraction for Handwritten Numerals 375 recognition. A 1D DWT =-=[3]-=- and a 1D undecimated multiwavelet transform [4] have been applied onto the previously extracted contour of the digits, and the result fed into a MLP classifier. Multirresolution techniques have also ... |

13 |
Contour-Based Handwritten Numeral Recognition Using Multiwavelets and Neural Networks
- Chen, Bui, et al.
(Show Context)
Citation Context ... 5716, pp. 374–383, 2009. c○ Springer-Verlag Berlin Heidelberg 2009Wavelet-Based Feature Extraction for Handwritten Numerals 375 recognition. A 1D DWT [3] and a 1D undecimated multiwavelet transform =-=[4]-=- have been applied onto the previously extracted contour of the digits, and the result fed into a MLP classifier. Multirresolution techniques have also been used in conjunction with more complex class... |

5 |
A new wavelet-based texture descriptor for image retrieval
- Ves, Ruedin, et al.
- 2007
(Show Context)
Citation Context ...d to be a powerful tool for image analysis, because of their capability to discriminate details at different resolutions. They have given good results in edge detection [1] and texture identification =-=[2]-=-. Discrete wavelet transforms (DWT) have been used to extract features for digit P. Foggia, C. Sansone, and M. Vento (Eds.): ICIAP 2009, LNCS 5716, pp. 374–383, 2009. c○ Springer-Verlag Berlin Heidelb... |

5 | Target detection and recognition using two-dimensional continuous isotropic and anisotropic wavelets
- Antoine, Vandergheynst, et al.
(Show Context)
Citation Context ...y giving one principal orientation to the wavelet, via stretching one of its axes, and adding a rotational angle as a parameter to the transform [6]. It has translation, rotation and scale covariance =-=[7]-=- (the CWT is covariant under translations, because when applied to a translated image, it produces the translated CWT of the original image). This CWT has been applied for pattern recognition in image... |

4 |
On the choice of training set, architecture and combination rule of multiple mlp classifiers for multiresolution recognition of handwritten characters
- Bhattacharya, Vajda, et al.
- 2004
(Show Context)
Citation Context ...on levels) to the digits, a combination of multiple MLPs was used, each one being trained, with dynamic selection of training samples, for a specific level of (thresholded) approximation coefficients =-=[5]-=-. On the other hand, the 2D Continuous Wavelet Transform (CWT) performs a scale-space analysis on images, by calculating the correlation between an image and a 2D wavelet, at different scales and loca... |

4 |
Pose estimation of SAR imagery using the two dimensional continuous waelet transform
- Kaplan, Murenzi
- 2003
(Show Context)
Citation Context ...ation in the image. 2.1 2D Mexican Hat: Isotropic or Anisotropic For our wavelet, we choose the Mexican Hat (MH), which is stretched in the direction of one of the axes in accordance with parameter ɛ =-=[10]-=-: ψMH(x1,x2) =(2−(x 2 1 + x22 )) e−(x2 1 ɛ +x2 2 /ɛ)/2 . (3) is the Laplacian of g(x1,x2) = e −(x2 1 +x2 2 )/2 ,a Note that when ɛ = 1, ψMH bidimensional Gaussian; it is isotropic, and in that case th... |

3 | Directional Continuous Wavelet Transform Applied to Handwritten Numerals Recognition Using Neural Networks
- Romero, Seijas, et al.
- 2007
(Show Context)
Citation Context ...to a translated image, it produces the translated CWT of the original image). This CWT has been applied for pattern recognition in images [8], and has given satisfactory results for digit recognition =-=[9]-=-. We use it here to extract a shape-preserving smaller version of the digits and to build a complementary vector with information on orientation, gradients and curvature at different scales. We implem... |

2 |
Exploring wavelet transforms for morphological differentiation between functionally different cat retinal ganglion cells
- Jelinek, Cesar, et al.
- 2003
(Show Context)
Citation Context ...g(x1,x2) and ψ2(x1,x2) = ∂x1 ∂g(x1,x2) , (5) ∂x2 which have 2 vanishing moments and can be interpreted as a multiresolution differential operator. With both wavelets we construct the wavelet gradient =-=[11]-=- at scale a and at each position in the image: Tψ(b, a) =[Sψ1(b, a, 0),Sψ2(b, a, 0)]. (6) Sψ1(b, a, 0), the first component of Tψ(b, a) in Eq. (6), is the horizontal wavelet gradient. Integrating by p... |

1 |
P.: A novel classifier for handwritten numeral recognition
- Wen, Shi
- 2008
(Show Context)
Citation Context ...cause their preprocessing is followed by a more complex classifier. Recently a classifier (with no preprocessing) was presented, based on the Bhattacharya distance and combined with a kernel approach =-=[15]-=-, giving a test error of 1.8% for MNIST; our results are better than theirs. We plan to investigate further the properties of our preprocessing technique in order to reduce the error rate percentage. ... |