Character Recognition Based on DTW-Radon

Santosh, K. C.

doi:10.1109/icdar.2011.61

Cited by 30 publications

(3 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Being one among them, handcrafted features can be used for the detection and recognition of objects. Emphasizing the task of character recognition, in Santosh (2011) author provides an approach using the DTW-Radon feature. The paper by Banerjee et al (2010) uses SVM along with SIFT (Lowe 2004) features for classifying objects.…”

Section: Related Workmentioning

confidence: 99%

An eigenvector approach for obtaining scale and orientation invariant classification in convolutional neural networks

Chathoth¹,

Mishra²,

Mishra³

et al. 2021

Adv. in Comp. Int.

View full text Add to dashboard Cite

The convolution neural networks are well known for their efficiency in detecting and classifying objects once adequately trained. Though they address shift in-variance up to a limit, appreciable rotation and scale in-variances are not guaranteed by many of the existing CNN architectures, making them sensitive towards input image or feature map rotation and scale variations. Many attempts have been made in the past to acquire rotation and scale in-variances in CNNs. In this paper, an efficient approach is proposed for incorporating rotation and scale in-variances in CNN-based classifications, based on eigenvectors and eigenvalues of the image covariance matrix. Without demanding any training data augmentation or CNN architectural change, the proposed method, 'Scale and Orientation Corrected Networks (SOCN)', achieves better rotation and scale-invariant performances. SOCN proposes a scale and orientation correction step for images before baseline CNN training and testing. Being a generalized approach, SOCN can be combined with any baseline CNN to improve its rotational and scale in-variance performances. We demonstrate the proposed approach's scale and orientation invariant classification ability with several real cases ranging from scale and orientation invariant character recognition to orientation invariant image classification, with different suitable baseline architectures. The proposed approach of SOCN, though is simple, outperforms the current state of the art scale and orientation invariant classifiers comparatively with minimal training and testing time. KeywordsRotation in-variance • Scale invariance • Eigenvectors • Eigen values • Principal component • CNN B Deepak Mishra

show abstract

Section: Related Workmentioning

confidence: 99%

An eigenvector approach for obtaining scale and orientation invariant classification in convolutional neural networks

Chathoth¹,

Mishra²,

Mishra³

et al. 2021

Adv. in Comp. Int.

View full text Add to dashboard Cite

show abstract

“…followed by a preprocessing step. Besides, to avoid compressing too much character representation into a single feature vector, DTW-based Radon features can be applied as powerful character shape descriptors (Santosh, 2011;Santosh and Wendling, 2015). Prevailing classification methods for character recognition, including statistical approaches, support vector machine, artificial neural network (ANN), and combined classifiers, are mainly based on feature vectors extracted from character images.…”

Section: Methodsmentioning

confidence: 99%

A New Database of Digits Extracted from Coins with Hard-to-Segment Foreground for Optical Character Recognition Evaluation

Pan

Tougne

2017

Front. ICT

View full text Add to dashboard Cite

Since the release date struck on a coin is important information of its monetary type, recognition of extracted digits may assist in identification of monetary types. However, digit images extracted from coins are challenging for conventional optical character recognition methods because the foreground of such digits has very often the same color as their background. In addition, other noises, including the wear of coin metal, make it more difficult to obtain a correct segmentation of the character shape. To address those challenges, this article presents the CoinNUMS database for automatic digit recognition. The database CoinNUMS, containing 3,006 digit images, is divided into three subsets. The first subset CoinNUMS_geni consists of 606 digit images manually cropped from high-resolution photographs of well-conserved coins from GENI coin photographs; the second subset CoinNUMS_pcgs_a consists of 1,200 digit images automatically extracted from a subset of the USA_Grading numismatic database containing coins in different quality; the last subset CoinNUMS_pcgs_m consists of 1,200 digit images manually extracted from the same coin photographs as CoinNUMS_pcgs_a. In CoinNUMS_pcgs_a and CoinNUMS_pcgs_m, the digit images are extracted from the release date. In CoinNUMS_geni, the digit images can come from the cropped date, the face value, or any other legends containing digits in the coin. To show the difficulty of these databases, we have tested recognition algorithms of the literature. The database and the results of the tested algorithms will be freely available on a dedicated website.

show abstract

“…Several generic shapes descriptors have been applied to this kind of shapes, and a general overview can be found in [1]. Among them, we can highlight the curvature scale space (CSS) descriptor [2] which successively blurs the shape contour by convolving it with a Gaussian kernel, the Shape Context [3], which selects n points from the contour of the shape and computes the distribution of the distance and angle between them, or the radon-based method proposed in [4], which uses DTW to match corresponding pairs of radon histograms at every projecting angle. These descriptors are robust to deformations, however, wether they can only deal with some specific shapes or they are computationally expensive, they can not be applied to all the tasks in the "handwritten" domain.…”

Section: Introductionmentioning

confidence: 99%

Deformable HOG-Based Shape Descriptor

Almazán

Fornés

Valveny

2013

2013 12th International Conference on Document Analysis and Recognition

View full text Add to dashboard Cite

In this paper we deal with the problem of recognizing handwritten shapes. We present a new deformable feature extraction method that adapts to the shape to be described, dealing in this way with the variability introduced in the handwriting domain. It consists in a selection of the regions that best define the shape to be described, followed by the computation of histograms of oriented gradients-based features over these points. Our results significantly outperform other descriptors in the literature for the task of hand-drawn shape recognition and handwritten word retrieval.

show abstract

Character Recognition Based on DTW-Radon

Cited by 30 publications

References 25 publications

An eigenvector approach for obtaining scale and orientation invariant classification in convolutional neural networks

An eigenvector approach for obtaining scale and orientation invariant classification in convolutional neural networks

A New Database of Digits Extracted from Coins with Hard-to-Segment Foreground for Optical Character Recognition Evaluation

Deformable HOG-Based Shape Descriptor

Contact Info

Product

Resources

About