The Experts below are selected from a list of 9030 Experts worldwide ranked by ideXlab platform
Horst Bunke - One of the best experts on this subject based on the ideXlab platform.
-
graph similarity features for hmm based Handwriting Recognition in historical documents
International Conference on Frontiers in Handwriting Recognition, 2010Co-Authors: Andreas Fischer, Kaspar Riesen, Horst BunkeAbstract:Automatic transcription of historical documents is vital for the creation of digital libraries. In this paper we propose graph similarity features as a novel descriptor for Handwriting Recognition in historical documents based on Hidden Markov Models. Using a structural graph-based representation of text images, a sequence of graph similarity features is extracted by means of dissimilarity embedding with respect to a set of character prototypes. On the medieval Parzival data set it is demonstrated that the proposed structural descriptor significantly outperforms two well-known statistical reference descriptors for single word Recognition.
-
a novel connectionist system for unconstrained Handwriting Recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009Co-Authors: Alex Graves, Marcus Liwicki, Horst Bunke, Santiago Fernandez, R Bertolami, Jurgen SchmidhuberAbstract:Recognizing lines of unconstrained handwritten text is a challenging task. The difficulty of segmenting cursive or overlapping characters, combined with the need to exploit surrounding context, has led to low Recognition rates for even the best current recognizers. Most recent progress in the field has been made either through improved preprocessing or through advances in language modeling. Relatively little work has been done on the basic Recognition algorithms. Indeed, most systems rely on the same hidden Markov models that have been used for decades in speech and Handwriting Recognition, despite their well-known shortcomings. This paper proposes an alternative approach based on a novel type of recurrent neural network, specifically designed for sequence labeling tasks where the data is hard to segment and contains long-range bidirectional interdependencies. In experiments on two large unconstrained Handwriting databases, our approach achieves word Recognition accuracies of 79.7 percent on online data and 74.1 percent on offline data, significantly outperforming a state-of-the-art HMM-based system. In addition, we demonstrate the network's robustness to lexicon size, measure the individual influence of its hidden layers, and analyze its use of context. Last, we provide an in-depth discussion of the differences between the network and HMMs, suggesting reasons for the network's superior performance.
-
unconstrained on line Handwriting Recognition with recurrent neural networks
Neural Information Processing Systems, 2007Co-Authors: Alex Graves, Marcus Liwicki, Jurgen Schmidhuber, Horst Bunke, Santiago FernandezAbstract:In online Handwriting Recognition the trajectory of the pen is recorded during writing. Although the trajectory provides a compact and complete representation of the written output, it is hard to transcribe directly, because each letter is spread over many pen locations. Most Recognition systems therefore employ sophisticated preprocessing techniques to put the inputs into a more localised form. However these techniques require considerable human effort, and are specific to particular languages and alphabets. This paper describes a system capable of directly transcribing raw online Handwriting data. The system consists of an advanced recurrent neural network with an output layer designed for sequence labelling, combined with a probabilistic language model. In experiments on an unconstrained online database, we record excellent results using either raw or preprocessed data, well outperforming a state-of-the-art HMM based system in both cases.
-
A novel approach to on-line Handwriting Recognition based on bidirectional long short-term memory networks
Proc. 9th Int. Conf. on Document Analysis and Recognition, 2007Co-Authors: Marcus Liwicki, Alex Graves, Horst Bunke, Jurgen SchmidhuberAbstract:In this paper we introduce a new connectionist approach to on-line Handwriting Recognition and address in partic- ular the problem of recognizing handwritten whiteboard notes. The approach uses a bidirectional recurrent neu- ral network with the long short-term memory architecture. We use a recently introduced objective function, known as Connectionist Temporal Classification (CTC), that directly trains the network to label unsegmented sequence data. Our new system achieves a word Recognition rate of 74.0%, compared with 65.4%using a previously developed HMM- based Recognition system.
-
offline Handwriting Recognition using synthetic training data produced by means of a geometrical distortion model
International Journal of Pattern Recognition and Artificial Intelligence, 2004Co-Authors: Tamas Varga, Horst BunkeAbstract:A perturbation model for the generation of synthetic textlines from existing cursively handwritten lines of text produced by human writers is presented. The goal of synthetic textline generation is to improve the performance of an offline cursive Handwriting Recognition system by providing it with additional training data. It can be expected that by adding synthetic training data the variability of the training set improves, which leads to a higher Recognition rate. On the other hand, synthetic training data may bias a recognizer towards unnatural Handwriting styles, which could lead to a deterioration of the Recognition rate. In this paper the proposed perturbation model is evaluated under several experimental conditions, and it is shown that significant improvement of the Recognition performance is possible even when the original training set is large and the textlines are provided by a large number of different writers.
Jurgen Schmidhuber - One of the best experts on this subject based on the ideXlab platform.
-
Convolutional neural network committees for handwritten character classification
Proceedings of the International Conference on Document Analysis and Recognition ICDAR, 2011Co-Authors: Dan C. Cireşan, Ueli Meier, Luca Maria Gambardella, Jurgen SchmidhuberAbstract:In 2010, after many years of stagnation, the MNIST Handwriting Recognition benchmark record dropped from 0.40% error rate to 0.35%. Here we report 0.27% for a committee of seven deep CNNs trained on graphics cards, narrowing the gap to human performance. We also apply the same architecture to NIST SD 19, a more challenging dataset including lower and upper case letters. A committee of seven CNNs obtains the best results published so far for both NIST digits and NIST letters. The robustness of our method is verified by analyzing 78125 different 7-net committees.
-
a novel connectionist system for unconstrained Handwriting Recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009Co-Authors: Alex Graves, Marcus Liwicki, Horst Bunke, Santiago Fernandez, R Bertolami, Jurgen SchmidhuberAbstract:Recognizing lines of unconstrained handwritten text is a challenging task. The difficulty of segmenting cursive or overlapping characters, combined with the need to exploit surrounding context, has led to low Recognition rates for even the best current recognizers. Most recent progress in the field has been made either through improved preprocessing or through advances in language modeling. Relatively little work has been done on the basic Recognition algorithms. Indeed, most systems rely on the same hidden Markov models that have been used for decades in speech and Handwriting Recognition, despite their well-known shortcomings. This paper proposes an alternative approach based on a novel type of recurrent neural network, specifically designed for sequence labeling tasks where the data is hard to segment and contains long-range bidirectional interdependencies. In experiments on two large unconstrained Handwriting databases, our approach achieves word Recognition accuracies of 79.7 percent on online data and 74.1 percent on offline data, significantly outperforming a state-of-the-art HMM-based system. In addition, we demonstrate the network's robustness to lexicon size, measure the individual influence of its hidden layers, and analyze its use of context. Last, we provide an in-depth discussion of the differences between the network and HMMs, suggesting reasons for the network's superior performance.
-
offline Handwriting Recognition with multidimensional recurrent neural networks
Neural Information Processing Systems, 2008Co-Authors: Alex Graves, Jurgen SchmidhuberAbstract:Offline Handwriting Recognition—the automatic transcription of images of handwritten text—is a challenging task that combines computer vision with sequence learning. In most systems the two elements are handled separately, with sophisticated preprocessing techniques used to extract the image features and sequential models such as HMMs used to provide the transcriptions. By combining two recent innovations in neural networks—multidimensional recurrent neural networks and connectionist temporal classification—this paper introduces a globally trained offline Handwriting recogniser that takes raw pixel data as input. Unlike competing systems, it does not require any alphabet specific preprocessing, and can therefore be used unchanged for any language. Evidence of its generality and power is provided by data from a recent international Arabic Recognition competition, where it outperformed all entries (91.4% accuracy compared to 87.2% for the competition winner) despite the fact that neither author understands a word of Arabic.
-
unconstrained on line Handwriting Recognition with recurrent neural networks
Neural Information Processing Systems, 2007Co-Authors: Alex Graves, Marcus Liwicki, Jurgen Schmidhuber, Horst Bunke, Santiago FernandezAbstract:In online Handwriting Recognition the trajectory of the pen is recorded during writing. Although the trajectory provides a compact and complete representation of the written output, it is hard to transcribe directly, because each letter is spread over many pen locations. Most Recognition systems therefore employ sophisticated preprocessing techniques to put the inputs into a more localised form. However these techniques require considerable human effort, and are specific to particular languages and alphabets. This paper describes a system capable of directly transcribing raw online Handwriting data. The system consists of an advanced recurrent neural network with an output layer designed for sequence labelling, combined with a probabilistic language model. In experiments on an unconstrained online database, we record excellent results using either raw or preprocessed data, well outperforming a state-of-the-art HMM based system in both cases.
-
A novel approach to on-line Handwriting Recognition based on bidirectional long short-term memory networks
Proc. 9th Int. Conf. on Document Analysis and Recognition, 2007Co-Authors: Marcus Liwicki, Alex Graves, Horst Bunke, Jurgen SchmidhuberAbstract:In this paper we introduce a new connectionist approach to on-line Handwriting Recognition and address in partic- ular the problem of recognizing handwritten whiteboard notes. The approach uses a bidirectional recurrent neu- ral network with the long short-term memory architecture. We use a recently introduced objective function, known as Connectionist Temporal Classification (CTC), that directly trains the network to label unsegmented sequence data. Our new system achieves a word Recognition rate of 74.0%, compared with 65.4%using a previously developed HMM- based Recognition system.
Alex Graves - One of the best experts on this subject based on the ideXlab platform.
-
a novel connectionist system for unconstrained Handwriting Recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009Co-Authors: Alex Graves, Marcus Liwicki, Horst Bunke, Santiago Fernandez, R Bertolami, Jurgen SchmidhuberAbstract:Recognizing lines of unconstrained handwritten text is a challenging task. The difficulty of segmenting cursive or overlapping characters, combined with the need to exploit surrounding context, has led to low Recognition rates for even the best current recognizers. Most recent progress in the field has been made either through improved preprocessing or through advances in language modeling. Relatively little work has been done on the basic Recognition algorithms. Indeed, most systems rely on the same hidden Markov models that have been used for decades in speech and Handwriting Recognition, despite their well-known shortcomings. This paper proposes an alternative approach based on a novel type of recurrent neural network, specifically designed for sequence labeling tasks where the data is hard to segment and contains long-range bidirectional interdependencies. In experiments on two large unconstrained Handwriting databases, our approach achieves word Recognition accuracies of 79.7 percent on online data and 74.1 percent on offline data, significantly outperforming a state-of-the-art HMM-based system. In addition, we demonstrate the network's robustness to lexicon size, measure the individual influence of its hidden layers, and analyze its use of context. Last, we provide an in-depth discussion of the differences between the network and HMMs, suggesting reasons for the network's superior performance.
-
offline Handwriting Recognition with multidimensional recurrent neural networks
Neural Information Processing Systems, 2008Co-Authors: Alex Graves, Jurgen SchmidhuberAbstract:Offline Handwriting Recognition—the automatic transcription of images of handwritten text—is a challenging task that combines computer vision with sequence learning. In most systems the two elements are handled separately, with sophisticated preprocessing techniques used to extract the image features and sequential models such as HMMs used to provide the transcriptions. By combining two recent innovations in neural networks—multidimensional recurrent neural networks and connectionist temporal classification—this paper introduces a globally trained offline Handwriting recogniser that takes raw pixel data as input. Unlike competing systems, it does not require any alphabet specific preprocessing, and can therefore be used unchanged for any language. Evidence of its generality and power is provided by data from a recent international Arabic Recognition competition, where it outperformed all entries (91.4% accuracy compared to 87.2% for the competition winner) despite the fact that neither author understands a word of Arabic.
-
unconstrained on line Handwriting Recognition with recurrent neural networks
Neural Information Processing Systems, 2007Co-Authors: Alex Graves, Marcus Liwicki, Jurgen Schmidhuber, Horst Bunke, Santiago FernandezAbstract:In online Handwriting Recognition the trajectory of the pen is recorded during writing. Although the trajectory provides a compact and complete representation of the written output, it is hard to transcribe directly, because each letter is spread over many pen locations. Most Recognition systems therefore employ sophisticated preprocessing techniques to put the inputs into a more localised form. However these techniques require considerable human effort, and are specific to particular languages and alphabets. This paper describes a system capable of directly transcribing raw online Handwriting data. The system consists of an advanced recurrent neural network with an output layer designed for sequence labelling, combined with a probabilistic language model. In experiments on an unconstrained online database, we record excellent results using either raw or preprocessed data, well outperforming a state-of-the-art HMM based system in both cases.
-
A novel approach to on-line Handwriting Recognition based on bidirectional long short-term memory networks
Proc. 9th Int. Conf. on Document Analysis and Recognition, 2007Co-Authors: Marcus Liwicki, Alex Graves, Horst Bunke, Jurgen SchmidhuberAbstract:In this paper we introduce a new connectionist approach to on-line Handwriting Recognition and address in partic- ular the problem of recognizing handwritten whiteboard notes. The approach uses a bidirectional recurrent neu- ral network with the long short-term memory architecture. We use a recently introduced objective function, known as Connectionist Temporal Classification (CTC), that directly trains the network to label unsegmented sequence data. Our new system achieves a word Recognition rate of 74.0%, compared with 65.4%using a previously developed HMM- based Recognition system.
S Manke - One of the best experts on this subject based on the ideXlab platform.
-
a connectionist recognizer for on line cursive Handwriting Recognition
International Conference on Acoustics Speech and Signal Processing, 1994Co-Authors: S Manke, U BodenhausenAbstract:Shows how the multi-state time delay neural network (MS-TDNN), which is already used successfully in continuous speech Recognition tasks, can be applied both to online single character and cursive (continuous) Handwriting Recognition. The MS-TDNN integrates the high accuracy single character Recognition capabilities of a TDNN with a non-linear time alignment procedure (dynamic time warping algorithm) for finding stroke and character boundaries in isolated, handwritten characters and words. In this approach each character is modelled by up to 3 different states and words are represented as a sequence of these characters. The authors describe the basic MS-TDNN architecture and the input features used in the paper, and present results (up to 97.7% word Recognition rate) both on writer dependent/independent, single character Recognition tasks and writer dependent, cursive Handwriting tasks with varying vocabulary sizes up to 20000 words. >
-
the use of dynamic writing information in a connectionist on line cursive Handwriting Recognition system
Neural Information Processing Systems, 1994Co-Authors: S Manke, Michael Finke, Alex WaibelAbstract:In this paper we present NPen++, a connectionist system for writer independent, large vocabulary on-line cursive Handwriting Recognition. This system combines a robust input representation, which preserves the dynamic writing information, with a neural network architecture, a so called Multi-State Time Delay Neural Network (MS-TDNN), which integrates Recognition and segmentation in a single framework. Our preprocessing transforms the original coordinate sequence into a (still temporal) sequence of feature vectors, which combine strictly local features, like curvature or writing direction, with a bitmap-like representation of the coordinate's proximity. The MS-TDNN architecture is well suited for handling temporal sequences as provided by this input representation. Our system is tested both on writer dependent and writer independent tasks with vocabulary sizes ranging from 400 up to 20,000 words. For example, on a 20,000 word vocabulary we achieve word Recognition rates up to 88.9% (writer dependent) and 84.1% (writer independent) without using any language models.
Simon Gunter - One of the best experts on this subject based on the ideXlab platform.
-
combination of three classifiers with different architectures for handwritten word Recognition
International Conference on Frontiers in Handwriting Recognition, 2004Co-Authors: Simon Gunter, Horst BunkeAbstract:The study of multiple classifier systems has become an area of intensive research in pattern Recognition recently. Also in Handwriting Recognition, systems combining several classifiers have been investigated. In this paper the combination of three classifiers for handwritten word Recognition with different architectures is studied. In addition a new ensemble method working with several base classifiers is applied and the results of the ensemble method are compared to the results of the combination of the three classifiers. In the experiments a large-scale handwritten word Recognition task is considered.
-
feature selection algorithms for the generation of multiple classifier systems and their application to handwritten word Recognition
Pattern Recognition Letters, 2004Co-Authors: Simon Gunter, Horst BunkeAbstract:The study of multiple classifier systems has become an area of intensive research in pattern Recognition recently. Also in Handwriting Recognition, systems combining several classifiers have been investigated. In this paper new methods for the creation of classifier ensembles based on feature selection algorithms are introduced. Those new methods are evaluated and compared to existing approaches in the context of handwritten word Recognition, using a hidden Markov model recognizer as basic classifier.
-
creation of classifier ensembles for handwritten word Recognition using feature selection algorithms
International Conference on Frontiers in Handwriting Recognition, 2002Co-Authors: Simon Gunter, Horst BunkeAbstract:The study of multiple classifier systems has become an area of intensive research in pattern Recognition. Also in Handwriting, Recognition, systems combining several classifiers have been investigated. In the paper new methods for the creation of classifier ensembles based on feature selection algorithms are introduced. These new methods are evaluated and compared to existing approaches in the context of handwritten word Recognition, using a hidden Markov model recognizer as basic classifier.