Wick, Christoph

OCR4all - An Open-Source Tool Providing a (Semi-)Automatic OCR Workflow for Historical Printings. Reul, Christian; Christ, Dennis; Hartelt, Alexander; Balbach, Nico; Wehner, Maximilian; Springmann, Uwe; Wick, Christoph; Grundig, Christine; Büttner, Andreas; Puppe, Frank. In ArXiv Preprints (submitted to MDPI - Applied Sciences). 2019.

[ BibTeX ]
[ URL ]

@article{reul2019ocr4all,
  abstract = {Optical Character Recognition (OCR) on historical printings is a challenging task mainly due to the complexity of the layout and the highly variant typography. Nevertheless, in the last few years great progress has been made in the area of historical OCR, resulting in several powerful open-source tools for preprocessing, layout recognition and segmentation, character recognition and post-processing. The drawback of these tools often is their limited applicability by non-technical users like humanist scholars and in particular the combined use of several tools in a workflow. In this paper we present an open-source OCR software called OCR4all, which combines state-of-the-art OCR components and continuous model training into a comprehensive workflow. A comfortable GUI allows error corrections not only in the final output, but already in early stages to minimize error propagations. Further on, extensive configuration capabilities are provided to set the degree of automation of the workflow and to make adaptations to the carefully selected default parameters for specific printings, if necessary. Experiments showed that users with minimal or no experience were able to capture the text of even the earliest printed books with manageable effort and great quality, achieving excellent character error rates (CERs) below 0.5%. The fully automated application on 19th century novels showed that OCR4all can considerably outperform the commercial state-of-the-art tool ABBYY Finereader on moderate layouts if suitably pretrained mixed OCR models are available. The architecture of OCR4all allows the easy integration (or substitution) of newly developed tools for its main components by standardized interfaces like PageXML, thus aiming at continual higher automation for historical printings.},
  author = {Reul, Christian and Christ, Dennis and Hartelt, Alexander and Balbach, Nico and Wehner, Maximilian and Springmann, Uwe and Wick, Christoph and Grundig, Christine and Büttner, Andreas and Puppe, Frank},
  journal = {ArXiv Preprints (submitted to MDPI - Applied Sciences)},
  keywords = {myown},
  title = {OCR4all - An Open-Source Tool Providing a (Semi-)Automatic OCR Workflow for Historical Printings},
  year = 2019
}

{OMMR}4all — a {Semiautomatic} {Online} {Editor} for {Medieval} {Music} {Notations}. Wick, Christoph; Puppe, Frank. In 2nd {International} {Workshop} on {Reading} {Music} {Systems}, J. Calvo-Zaragoza, A. Pacha (eds.), pp. 31–34. Delft, The Netherlands, 2019.

[ BibTeX ]
[ URL ]

@inproceedings{wick_ommr4all_2019,
  address = {Delft, The Netherlands},
  author = {Wick, Christoph and Puppe, Frank},
  booktitle = {2nd {International} {Workshop} on {Reading} {Music} {Systems}},
  editor = {Calvo-Zaragoza, Jorge and Pacha, Alexander},
  keywords = {myown},
  pages = {31–34},
  title = {{OMMR}4all — a {Semiautomatic} {Online} {Editor} for {Medieval} {Music} {Notations}},
  year = 2019
}

Automatic Semantic Text Tagging on Historical Lexica by Combining OCR and Typography Classification. Reul, Christian; Göttel, Sebastian; Springmann, Uwe; Wick, Christoph; Würzner, Kay-Michael; Puppe, Frank. In Proceedings of the 3rd International Conference on Digital Access to Textual Cultural Heritage. 2019.

[ BibTeX ]

@article{reul2019automatic,
  abstract = {When converting historical lexica into electronic form the goal is not only to obtain a high quality OCR result for the text but also to perform a precise automatic recognition of typographical attributes in order to capture the logical structure. For that purpose, we present a method that enables a fine-grained typography classification by training an open source OCR engine both on traditional OCR and typography recognition and show how to map the obtained typography information to the OCR recognized text output. As a test case, we used a German dictionary (Sander's "Wörterbuch der Deutschen Sprache") from the 19th century, which comprises a particularly complex semantic function of typography. Despite the very challenging material, we achieved a character error rate below 0.4% and a typography recognition that assigns the correct label to close to 99% of the words. In contrast to many existing methods, our novel approach works with real historical data and can deal with frequent typography changes even within lines.},
  author = {Reul, Christian and Göttel, Sebastian and Springmann, Uwe and Wick, Christoph and Würzner, Kay-Michael and Puppe, Frank},
  journal = {Proceedings of the 3rd International Conference on Digital Access to Textual Cultural Heritage},
  keywords = {myown},
  title = {Automatic Semantic Text Tagging on Historical Lexica by Combining OCR and Typography Classification},
  year = 2019
}

Staff, Symbol and Melody Detection of Medieval Manuscripts Written in Square Notation Using Deep Fully Convolutional Networks. Wick, Christoph; Hartelt, Alexander; Puppe, Frank. In Applied Sciences, 9(13). 2019.

[ BibTeX ]
[ URL ]
[ Download ]

@article{app9132646,
  abstract = {Even today, the automatic digitisation of scanned documents in general, but especially the automatic optical music recognition (OMR) of historical manuscripts, still remains an enormous challenge, since both handwritten musical symbols and text have to be identified. This paper focuses on the Medieval so-called square notation developed in the 11th–12th century, which is already composed of staff lines, staves, clefs, accidentals, and neumes that are roughly spoken connected single notes. The aim is to develop an algorithm that captures both the neumes, and in particular its melody, which can be used to reconstruct the original writing. Our pipeline is similar to the standard OMR approach and comprises a novel staff line and symbol detection algorithm based on deep Fully Convolutional Networks (FCN), which perform pixel-based predictions for either staff lines or symbols and their respective types. Then, the staff line detection combines the extracted lines to staves and yields an F 1 -score of over 99% for both detecting lines and complete staves. For the music symbol detection, we choose a novel approach that skips the step to identify neumes and instead directly predicts note components (NCs) and their respective affiliation to a neume. Furthermore, the algorithm detects clefs and accidentals. Our algorithm predicts the symbol sequence of a staff with a diplomatic symbol accuracy rate (dSAR) of about 87%, which includes symbol type and location. If only the NCs without their respective connection to a neume, all clefs and accidentals are of interest, the algorithm reaches an harmonic symbol accuracy rate (hSAR) of approximately 90%. In general, the algorithm recognises a symbol in the manuscript with an F 1 -score of over 96%.},
  author = {Wick, Christoph and Hartelt, Alexander and Puppe, Frank},
  journal = {Applied Sciences},
  keywords = {dissertation},
  number = 13,
  title = {Staff, Symbol and Melody Detection of Medieval Manuscripts Written in Square Notation Using Deep Fully Convolutional Networks},
  volume = 9,
  year = 2019
}

State of the Art Optical Character Recognition of 19th Century Fraktur Scripts using Open Source Engines. Reul, Christian; Springmann, Uwe; Wick, Christoph; Puppe, Frank. In DHd 2019 Digital Humanities: multimedial & multimodal. 2019.

[ BibTeX ]
[ URL ]

@article{reul2019state,
  abstract = {In this paper we evaluate Optical Character Recognition (OCR) of 19th century Fraktur scripts without book-specific training using mixed models, i.e. models trained to recognize a variety of fonts and typesets from previously unseen sources. We describe the training process leading to strong mixed OCR models and compare them to freely available models of the popular open source engines OCRopus and Tesseract as well as the commercial state of the art system ABBYY. For evaluation, we use a varied collection of unseen data from books, journals, and a dictionary from the 19th century. The experiments show that training mixed models with real data is superior to training with synthetic data and that the novel OCR engine Calamari outperforms the other engines considerably, on average reducing ABBYYs character error rate (CER) by over 70%, resulting in an average CER below 1%.},
  author = {Reul, Christian and Springmann, Uwe and Wick, Christoph and Puppe, Frank},
  journal = {DHd 2019 Digital Humanities: multimedial & multimodal},
  keywords = {myown},
  title = {State of the Art Optical Character Recognition of 19th Century Fraktur Scripts using Open Source Engines},
  year = 2019
}

Comparison of OCR Accuracy on Early Printed Books using the Open Source Engines Calamari and OCRopus. Wick, Christoph; Reul, Christian; Puppe, Frank. In Vol. 33, pp. 79–96. 2018.

[ BibTeX ]
[ Download ]

@book{wick2018comparison,
  author = {Wick, Christoph and Reul, Christian and Puppe, Frank},
  journal = {JLCL},
  keywords = {dissertation},
  number = 1,
  pages = {79-96},
  title = {Comparison of OCR Accuracy on Early Printed Books using the Open Source Engines Calamari and OCRopus},
  volume = 33,
  year = 2018
}

Improving OCR Accuracy on Early Printed Books by combining Pretraining, Voting, and Active Learning. Reul, Christian; Springmann, Uwe; Wick, Christoph; Puppe, Frank. In JLCL, 33(1), pp. 3–24. 2018.

[ BibTeX ]
[ Download ]

@article{noauthororeditor,
  author = {Reul, Christian and Springmann, Uwe and Wick, Christoph and Puppe, Frank},
  journal = {JLCL},
  keywords = {sys:relevantfor:uniwue_info6},
  number = 1,
  pages = {3-24},
  title = {Improving OCR Accuracy on Early Printed Books by combining Pretraining, Voting, and Active Learning},
  volume = 33,
  year = 2018
}

Improving OCR Accuracy on Early Printed Books by utilizing Cross Fold Training and Voting. Reul, Christian; Springmann, Uwe; Wick, Christoph; Puppe, Frank. 2017.

[ BibTeX ]
[ URL ]

@misc{reul2017ocrvoting,
  abstract = {In this paper we introduce a method that significantly reduces the character error rates for OCR text obtained from OCRopus models trained on early printed books. The method uses a combination of cross fold training and confidence based voting. After allocating the available ground truth in different subsets several training processes are performed, each resulting in a specific OCR model. The OCR text generated by these models then gets voted to determine the final output by taking the recognized characters, their alternatives, and the confidence values assigned to each character into consideration. Experiments on seven early printed books show that the proposed method outperforms the standard approach considerably by reducing the amount of errors by up to 50% and more.},
  author = {Reul, Christian and Springmann, Uwe and Wick, Christoph and Puppe, Frank},
  keywords = {das_2018_1},
  note = {cite arxiv:1711.09670},
  title = {Improving OCR Accuracy on Early Printed Books by utilizing Cross Fold Training and Voting},
  year = 2017
}

Fully Convolutional Neural Networks for Page Segmentation of Historical Document Images. Wick, Christoph; Puppe, Frank. 2017.

[ BibTeX ]
[ URL ]

@misc{wick2017fcnhistdoc,
  abstract = {We propose a high-performance fully convolutional neural network (FCN) for historical handwritten document segmentation that is designed to process a single page in one step. The advantage of this model beside its speed is its ability to directly learn from raw pixels instead of using preprocessing steps e. g. feature computation or superpixel generation. We show that this network yields better results than existing methods on different public data sets. For evaluation of this model we introduce a novel metric that is independent of ambiguous ground truth called Foreground Pixel Accuracy (FgPA). This pixel based measure only counts foreground pixels in the binarized page, any background pixel is omitted. The major advantage of this metric is, that it enables researchers to compare different segmentation methods on their ability to successfully segment text or pictures and not on their ability to learn and possibly overfit the peculiarities of an ambiguous hand-made ground truth segmentation.},
  author = {Wick, Christoph and Puppe, Frank},
  keywords = {das_2018_1},
  note = {cite arxiv:1711.07695Comment: 6 pages, 8 figures, conference},
  title = {Fully Convolutional Neural Networks for Page Segmentation of Historical Document Images},
  year = 2017
}

Playing Music in Just Intonation - A Dynamically Adapting Tuning Scheme. Stange, Karolin; Wick, Christoph; Hinrichsen, Haye. 2017.

[ BibTeX ]
[ URL ]
[ Download ]

@misc{stange2017playing,
  abstract = {We introduce a dynamically adapting tuning scheme for microtonal tuning of musical instruments, allowing the performer to play music in just intonation in any key. Unlike previous methods, which are based on a procedural analysis of the chordal structure, the suggested tuning scheme continually solves a system of linear equations without making explicit decisions. In complex situations, where not all intervals of a chord can be tuned according to just frequency ratios, the method automatically yields a tempered compromise. We outline the implementation of the algorithm in an open-source software project that we have provided in order to demonstrate the feasibility of the tuning method.},
  author = {Stange, Karolin and Wick, Christoph and Hinrichsen, Haye},
  keywords = {just_intonation},
  note = {cite arxiv:1706.04338Comment: 21 pages, 4 figures},
  title = {Playing Music in Just Intonation - A Dynamically Adapting Tuning Scheme},
  year = 2017
}

Leaf Identification Using a Deep Convolutional Neural Network. Wick, Christoph; Puppe, Frank. 2017.

[ BibTeX ]
[ URL ]

@misc{wick2017leafidentification,
  abstract = {Convolutional neural networks (CNNs) have become popular especially in computer vision in the last few years because they achieved outstanding performance on different tasks, such as image classifications. We propose a nine-layer CNN for leaf identification using the famous Flavia and Foliage datasets. Usually the supervised learning of deep CNNs requires huge datasets for training. However, the used datasets contain only a few examples per plant species. Therefore, we apply data augmentation and transfer learning to prevent our network from overfitting. The trained CNNs achieve recognition rates above 99% on the Flavia and Foliage datasets, and slightly outperform current methods for leaf classification.},
  author = {Wick, Christoph and Puppe, Frank},
  keywords = {cnn},
  note = {cite arxiv:1712.00967},
  title = {Leaf Identification Using a Deep Convolutional Neural Network},
  year = 2017
}

Transfer Learning for OCRopus Model Training on Early Printed Books. Reul, Christian; Wick, Christoph; Springmann, Uwe; Puppe, Frank. 2017.

[ BibTeX ]
[ URL ]

@misc{reul2017transfer,
  abstract = {A method is presented that significantly reduces the character error rates for OCR text obtained from OCRopus models trained on early printed books when only small amounts of diplomatic transcriptions are available. This is achieved by building from already existing models during training instead of starting from scratch. To overcome the discrepancies between the set of characters of the pretrained model and the additional ground truth the OCRopus code is adapted to allow for alphabet expansion or reduction. The character set is now capable of flexibly adding and deleting characters from the pretrained alphabet when an existing model is loaded. For our experiments we use a self-trained mixed model on early Latin prints and the two standard OCRopus models on modern English and German Fraktur texts. The evaluation on seven early printed books showed that training from the Latin mixed model reduces the average amount of errors by 43% and 26%, respectively compared to training from scratch with 60 and 150 lines of ground truth, respectively. Furthermore, it is shown that even building from mixed models trained on data unrelated to the newly added training and test data can lead to significantly improved recognition results.},
  author = {Reul, Christian and Wick, Christoph and Springmann, Uwe and Puppe, Frank},
  keywords = {dissertation},
  note = {cite arxiv:1712.05586},
  title = {Transfer Learning for OCRopus Model Training on Early Printed Books},
  year = 2017
}

Deep Learning. Wick, Christoph. In Informatik-Spektrum, pp. 1–5. 2016.

[ BibTeX ]
[ URL ]

@article{Wick2016,
  author = {Wick, Christoph},
  journal = {Informatik-Spektrum},
  keywords = {sys:relevantfor:uniwue_info6},
  pages = {1–5},
  title = {Deep Learning},
  year = 2016
}

Entanglement formation under random interactions. Wick, Christoph; Um, Jaegon; Hinrichsen, Haye. 2015.

[ BibTeX ]
[ URL ]
[ Download ]

@misc{wick2015entanglement,
  abstract = {The temporal evolution of the entanglement between two qubits evolving by random interactions is studied analytically and numerically. Two different types of randomness are investigated. Firstly we analyze an ensemble of systems with randomly chosen but time-independent interaction Hamiltonians. Secondly we consider the case of a temporally fluctuating Hamiltonian, where the unitary evolution can be understood as a random walk on the SU (4) group manifold. As a by-product we compute the metric tensor and its inverse as well as the Laplace-Beltrami for SU (4).},
  author = {Wick, Christoph and Um, Jaegon and Hinrichsen, Haye},
  keywords = {myown},
  note = {cite arxiv:1508.01652v2.pdfComment: Latex, 24 pages, 4 figures, Supplement material in source archive},
  title = {Entanglement formation under random interactions},
  year = 2015
}

Dr. Christoph Wick

Projects

Publications

Teaching

Data privacy protection

Data privacy protection

Picture credits