Stefan Fiel

Writer Retrieval and Writer Identification Using Local Features

Writer identification determines the writer of one document among a number of known writers where at least one sample is known. Writer retrieval searches all documents of one particular writer by creating a ranking of the similarity of the handwriting in a dataset. This paper presents a method for writer retrieval and writer identification using local features and therefore the proposed method is not dependent on a binarization step. First the local features of the image are calculated and with the help of a predefined codebook an occurrence histogram can be created. This histogram is compared to determine the identity of the writer or the similarity of other handwritten documents. The proposed method has been evaluated on two datasets, namely the IAM dataset which contains 650 writers and the Trigraph Slant dataset which contains 47 writers. Experiments have shown that it can keep up with previous writer identification approaches. Regarding writer retrieval it outperforms previous methods.

Writer Identification and Writer Retrieval Using the Fisher Vector on Visual Vocabularies

In this paper a method for writer identification and writer retrieval is presented. Writer identification is the task of identifying the writer of a document out of a database of known writers. In contrast to identification, writer retrieval is the task of finding documents in a database according to the similarity of handwritings. The approach presented in this paper uses local features for this task. First a vocabulary is calculated by clustering features using a Gaussian Mixture Model and applying the Fisher kernel. For each document image the features are calculated and the Fisher Vector is generated using the vocabulary. The distance of this vector is then used as similarity measurement for the handwriting and can be used for writer identification and writer retrieval. The proposed method is evaluated on two datasets, namely the ICDAR 2011 Writer Identification Contest dataset which consists of 208 documents from 26 writers, and the CVL Database which contains 1539 documents from 309 writers. Experiments show that the proposed methods performs slightly better than previously presented writer identification approaches.

CVL-DataBase: An Off-Line Database for Writer Retrieval, Writer Identification and Word Spotting

In this paper a public database for writer retrieval, writer identification and word spotting is presented. The CVL-Database consists of 7 different handwritten texts (1 German and 6 English Texts) and 311 different writers. For each text an RGB color image (300 dpi) comprising the handwritten text and the printed text sample are available as well as a cropped version (only handwritten). A unique ID identifies the writer, whereas the bounding boxes for each single word are stored in an XML file. An evaluation of the best algorithms of the ICDAR and ICHFR writer identification contest has been performed on the CVL-database.

ICDAR 2013 Competition on Handwritten Digit Recognition (HDRC 2013)

This paper presents the results of the HDRC 2013 competition for recognition of handwritten digits organized in conjunction with ICDAR 2013. The general objective of this competition is to identify, evaluate and compare recent developments in character recognition and to introduce a new challenging dataset for benchmarking. We describe competition details including dataset and evaluation measures used, and give a comparative performance analysis of the nine (9) submitted methods along with a short description of the respective methodologies.

End-to-End Text Recognition Using Local Ternary Patterns, MSER and Deep Convolutional Nets

Text recognition in natural scene images is an application for several computer vision applications like licence plate recognition, automated translation of street signs, help for visually impaired people or image retrieval. In this work an end-to-end text recognition system is presented. For detection an AdaBoost ensemble with a modified Local Ternary Pattern (LTP) feature-set with a post-processing stage build upon Maximally Stable Extremely Region (MSER) is used. The text recognition is done using a deep Convolution Neural Network (CNN) trained with backpropagation. The system presented outperforms state of the art methods on the ICDAR 2003 dataset in the text-detection (F-Score: 74.2%), dictionary-driven cropped-word recognition (F-Score: 87.1%) and dictionary-driven end-to-end recognition (F-Score: 72.6%) tasks.

Writer Identification and Retrieval Using a Convolutional Neural Network

In this paper a novel method for writer identification and retrieval is presented. Writer identification is the process of finding the author of a specific document by comparing it to documents in a database where writers are known, whereas retrieval is the task of finding similar handwritings or all documents of a specific writer. The method presented is using Convolutional Neural Networks CNN to generate a feature vector for each writer, which is then compared with the precalculated feature vectors stored in the database. For the generation of this vector the CNN is trained on a database with known writers and after training the classification layer is cut off and the output of the second last fully connected layer is used as feature vector. For the identification a nearest neighbor classification is used. The evaluation is performed on the ICDAR2013 Competition on Writer Identification, ICDAR 2011 Writer Identification Contest, and the CVL-Database datasets. Experiments show, that this novel approach achieves better results to previously presented writer identification approaches.

Semi-automated document image clustering and retrieval

In this paper a semi-automated document image clustering and retrieval is presented to create links between different documents based on their content. Ideally the initial bundling of shuffled document images can be reproduced to explore large document databases. Structural and textural features, which describe the visual similarity, are extracted and used by experts (e.g. registrars) to interactively cluster the documents with a manually defined feature subset (e.g. checked paper, handwritten). The methods presented allow for the analysis of heterogeneous documents that contain printed and handwritten text and allow for a hierarchically clustering with different feature subsets in different layers.

Writer identification on historical Glagolitic documents

This work aims at automatically identifying scribes of historical Slavonic manuscripts. The quality of the ancient documents is partially degraded by faded-out ink or varying background. The writer identification method used is based on image features, which are described with Scale Invariant Feature Transform (SIFT) features. A visual vocabulary is used for the description of handwriting characteristics, whereby the features are clustered using a Gaussian Mixture Model and employing the Fisher kernel. The writer identification approach is originally designed for grayscale images of modern handwritings. But contrary to modern documents, the historical manuscripts are partially corrupted by background clutter and water stains. As a result, SIFT features are also found on the background. Since the method shows also good results on binarized images of modern handwritings, the approach was additionally applied on binarized images of the ancient writings. Experiments show that this preprocessing step leads to a significant performance increase: The identification rate on binarized images is 98.9%, compared to an identification rate of 87.6% gained on grayscale images.

Mass Digitization of Archival Documents using Mobile Phones

Digital copies of historical documents are needed for the Digital Humanities. Currently, cameras of standard mobile phones are able to capture documents with a resolution of about 330 dpi for document sizes up to DIN A4 (German standard, 297 x 210 mm), which allows a digitization of documents using a standard device. Thus, scholars are able to take images of documents in archives themselves without the need of book scanners or other devices. This paper presents a scanning app, which comprises a real time page detection, quality assessment (focus measure) and an automated detection of a page turn over if books are scanned. Additionally, a portable device - the ScanTent - to place the mobile phone during scanning is presented. The page detection is evaluated on the ICDAR2015 SmartDoc competition dataset and shows a reliable page detection with an average Jaccard index of 75%.

Investigation of Ancient Manuscripts based on Multispectral Imaging

This work is concerned with the digitization and analysis of historical documents. The investigation of the documents has been conducted in three successive interdisciplinary projects. The team involved in the projects consists of philologists, chemists and computer scientists specialized in the field of digital image processing. The manuscripts investigated are partially degraded since they have been infected by mold, are corrupted by background clutter or contain faded-out or even erased writings. Since these degradations impede a transcription by scholars and worsen the performance of automated document image analysis techniques, the documents have been imaged with a portable multispectral imaging system. By using this non-invasive investigation technique, the contrast of the faded out characters can be increased, compared to ordinary white light illumination. Post-processing techniques, such as dimension reduction tools, can be used to gain a further legibility increase. The resulting images are used as a basis for further document analysis methods. These methods have been especially designed for the historical documents investigated and involve Optical Character Recognition and writer identification. This paper presents an overview on selected methods that have been developed in the projects.