Results 1  10
of
116
Adaptive document image binarization
 PATTERN RECOGNITION
, 2000
"... A new method is presented for adaptive document image binarization, where the page is considered as a collection of subcomponents such as text, background and picture. The problems caused by noise, illumination and many source typerelated degradations are addressed. Two new algorithms are applied t ..."
Abstract

Cited by 205 (0 self)
 Add to MetaCart
A new method is presented for adaptive document image binarization, where the page is considered as a collection of subcomponents such as text, background and picture. The problems caused by noise, illumination and many source typerelated degradations are addressed. Two new algorithms are applied to determine a local threshold for each pixel. The performance evaluation of the algorithm utilizes test images with groundtruth, evaluation metrics for binarization of textual and synthetic images, and a weightbased ranking procedure for the final result presentation. The proposed algorithms were tested with images including different types of document components and degradations. The results were compared with a number of known techniques in the literature. The benchmarking results show that the method adapts and performs well in each case qualitatively and quantitatively.
Training Invariant Support Vector Machines
, 2002
"... Practical experience has shown that in order to obtain the best possible performance, prior knowledge about invariances of a classification problem at hand ought to be incorporated into the training procedure. We describe and review all known methods for doing so in support vector machines, provide ..."
Abstract

Cited by 184 (16 self)
 Add to MetaCart
Practical experience has shown that in order to obtain the best possible performance, prior knowledge about invariances of a classification problem at hand ought to be incorporated into the training procedure. We describe and review all known methods for doing so in support vector machines, provide experimental results, and discuss their respective merits. One of the significant new results reported in this work is our recent achievement of the lowest reported test error on the wellknown MNIST digit recognition benchmark task, with SVM training times that are also significantly faster than previous SVM methods.
Representation Learning: A Review and New Perspectives
, 2012
"... The success of machine learning algorithms generally depends on data representation, and we hypothesize that this is because different representations can entangle and hide more or less the different explanatory factors of variation behind the data. Although specific domain knowledge can be used to ..."
Abstract

Cited by 153 (4 self)
 Add to MetaCart
The success of machine learning algorithms generally depends on data representation, and we hypothesize that this is because different representations can entangle and hide more or less the different explanatory factors of variation behind the data. Although specific domain knowledge can be used to help design representations, learning with generic priors can also be used, and the quest for AI is motivating the design of more powerful representationlearning algorithms implementing such priors. This paper reviews recent work in the area of unsupervised feature learning and joint training of deep learning, covering advances in probabilistic models, autoencoders, manifold learning, and deep architectures. This motivates longerterm unanswered questions about the appropriate objectives for learning good representations, for computing representations (i.e., inference), and the geometrical connections between representation learning, density estimation and manifold learning.
Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion
, 2010
"... ..."
Learning over Sets using Kernel Principal Angles
 Journal of Machine Learning Research
, 2003
"... We consider the problem of learning with instances defined over a space of sets of vectors. We derive a new positive definite kernel f (A,B) defined over pairs of matrices A,B based on the concept of principal angles between two linear subspaces. We show that the principal angles can be recovered ..."
Abstract

Cited by 105 (2 self)
 Add to MetaCart
(Show Context)
We consider the problem of learning with instances defined over a space of sets of vectors. We derive a new positive definite kernel f (A,B) defined over pairs of matrices A,B based on the concept of principal angles between two linear subspaces. We show that the principal angles can be recovered using only innerproducts between pairs of column vectors of the input matrices thereby allowing the original column vectors of A,B to be mapped onto arbitrarily highdimensional feature spaces.
A SelfCorrecting 100Font Classifier
, 1994
"... We have developed a practical scheme to take advantage of local typeface homogeneity to improve the accuracy of a character classifier. Given a polyfont classifier which is capable of recognizing any of 100 typefaces moderately well, our method allows it to specialize itself automatically to the sin ..."
Abstract

Cited by 66 (35 self)
 Add to MetaCart
We have developed a practical scheme to take advantage of local typeface homogeneity to improve the accuracy of a character classifier. Given a polyfont classifier which is capable of recognizing any of 100 typefaces moderately well, our method allows it to specialize itself automatically to the single  but otherwise unknown  typeface it is reading. Essentially, the classifier retrains itself after examining some of the images, guided at first by the preset classification boundaries of the given classifier, and later by the behavior of the retrained classifier. Experimental trials on 6.4M pseudorandomly distorted images show that the method improves on 95 of the 100 typefaces. It reduces the error rate by a factor of 2.5, averaged over 100 typefaces, when applied to an alphabet of 80 ASCII characters printed at ten point and digitized at 300 pixels/inch. This selfcorrecting method complements, and does not hinder, other methods for improving OCR accuracy, such as linguistic con...
Survey of the state of the art in human language technology
 Studies In Natural Language Processing, XIIXIII
, 1997
"... Sponsors: ..."
Global and Local Document Degradation Models
 In Proceedings of the International Conference on Document Analysis and Recognition
, 1993
"... Two sources of document degradation are modeled  i) perspective distortion that occurs while photocopying or scanning thick, bound documents, and ii) degradation due to perturbation in the optical scanning and digitization process: speckle, blurr, jitter, threshold. Perspective distortion is model ..."
Abstract

Cited by 59 (13 self)
 Add to MetaCart
(Show Context)
Two sources of document degradation are modeled  i) perspective distortion that occurs while photocopying or scanning thick, bound documents, and ii) degradation due to perturbation in the optical scanning and digitization process: speckle, blurr, jitter, threshold. Perspective distortion is modeled by studying the underlying perspective geometry of the optical system of photocopiers and scanners. An illumination model is described to account for the nonlinear intensity change occuring across a page in a perspectivedistorted document. The optical distortion process is modeled morphlogically. First a distance transform on the foreground is performed and followed by a random inversion of binary pixels where the probability of flip is a function of the distance of the pixel to the boundary of the foreground. Correlating the flipped pixels is modeled by a morphological closing operation. 1 Introduction There are many reasons for modeling document degradation. First, in order to study ...
Kernel Principal Angles for Classification Machines with Applications to Image Sequence Interpretation
, 2002
"... We consider the problem of learning with instances defined over a space of sets of vectors. We derive a new positive definite kernel f(A# B) defined over pairs of matrices A# B based on the concept of principal angles between two linear subspaces. We show that the principal angles can be recovered ..."
Abstract

Cited by 48 (6 self)
 Add to MetaCart
We consider the problem of learning with instances defined over a space of sets of vectors. We derive a new positive definite kernel f(A# B) defined over pairs of matrices A# B based on the concept of principal angles between two linear subspaces. We show that the principal angles can be recovered using only innerproducts between pairs of column vectors of the input matrices thereby allowing the original column vectors of A# B to be mapped onto arbitrarily highdimensional feature spaces.
Machine printed text and handwriting identification in noisy document images
 IEEE Transaction on Pattern Analysis and Machine Intelligence(PAMI
"... Abstract—In this paper, we address the problem of the identification of text in noisy document images. We are especially focused on segmenting and identifying between handwriting and machine printed text because: 1) Handwriting in a document often indicates corrections, additions, or other supplemen ..."
Abstract

Cited by 48 (6 self)
 Add to MetaCart
(Show Context)
Abstract—In this paper, we address the problem of the identification of text in noisy document images. We are especially focused on segmenting and identifying between handwriting and machine printed text because: 1) Handwriting in a document often indicates corrections, additions, or other supplemental information that should be treated differently from themain content and 2) the segmentation and recognition techniques requested for machine printed and handwritten text are significantly different. A novel aspect of our approach is that we treat noise as a separate class and model noise based on selected features. Trained Fisher classifiers are used to identify machine printed text and handwriting from noise and we further exploit context to refine the classification. AMarkov RandomFieldbased (MRF) approach is used to model the geometrical structure of the printed text, handwriting, and noise to rectify misclassifications. Experimental results show that our approach is robust and can significantly improve page segmentation in noisy document collections. Index Terms—Text identification, handwriting identification, Markov random field, postprocessing, noisy document image enhancement, document analysis. 1