Johannes Michael

Johannes Michael, Kurt Chudej, Jürgen Pannek

Capturing disused satellites in orbit and their controlled reentry is the aim of the DEOS space mission. Satellites that ran out of fuel or got damaged pose a threat to working projects in orbit. Additionally, the reentry of such objects endangers the population as the place of impact cannot be controlled anymore. This paper demonstrates the modelling of a rendezvous szenario between a controlled service satellite and an uncontrolled target. The situation is modelled via first order ordinary differental equations where a stable target is considered. In order to prevent a collision of the two spacecrafts and to ensure both satellites are docked at the end of the maneuver, additional state constraints, box contraints for the control and a time dependent rendezvous condition for the final time are added. The problem is formulated as an optimal control problem with Bolza type cost functional and solved using a full discretization approach in AMPL/IpOpt. Last, simulation results for capturing a tumbling satellite are given.

Tobias Grüning, Gundram Leifert, Tobias Strauß et al.

This work presents a two-stage text line detection method for historical documents. Each detected text line is represented by its baseline. In a first stage, a deep neural network called ARU-Net labels pixels to belong to one of the three classes: baseline, separator or other. The separator class marks beginning and end of each text line. The ARU-Net is trainable from scratch with manageably few manually annotated example images (less than 50). This is achieved by utilizing data augmentation strategies. The network predictions are used as input for the second stage which performs a bottom-up clustering to build baselines. The developed method is capable of handling complex layouts as well as curved and arbitrarily oriented text lines. It substantially outperforms current state-of-the-art approaches. For example, for the complex track of the cBAD: ICDAR2017 Competition on Baseline Detection the F-value is increased from 0.859 to 0.922. The framework to train and run the ARU-Net is open source.

Johannes Michael, Roger Labahn, Tobias Grüning et al.

Encoder-decoder models have become an effective approach for sequence learning tasks like machine translation, image captioning and speech recognition, but have yet to show competitive results for handwritten text recognition. To this end, we propose an attention-based sequence-to-sequence model. It combines a convolutional neural network as a generic feature extractor with a recurrent neural network to encode both the visual information, as well as the temporal context between characters in the input image, and uses a separate recurrent neural network to decode the actual character sequence. We make experimental comparisons between various attention mechanisms and positional encodings, in order to find an appropriate alignment between the input and output sequence. The model can be trained end-to-end and the optional integration of a hybrid loss allows the encoder to retain an interpretable and usable output, if desired. We achieve competitive results on the IAM and ICFHR2016 READ data sets compared to the state-of-the-art without the use of a language model, and we significantly improve over any recent sequence-to-sequence approaches.

Animesh Prasad, Hervé Déjean, Jean-Luc Meunier et al.

In this report, we present our findings from benchmarking experiments for information extraction on historical handwritten marriage records Esposalles from IEHHR - ICDAR 2017 robust reading competition. The information extraction is modeled as semantic labeling of the sequence across 2 set of labels. This can be achieved by sequentially or jointly applying handwritten text recognition (HTR) and named entity recognition (NER). We deploy a pipeline approach where first we use state-of-the-art HTR and use its output as input for NER. We show that given low resource setup and simple structure of the records, high performance of HTR ensures overall high performance. We explore the various configurations of conditional random fields and neural networks to benchmark NER on given certain noisy input. The best model on 10-fold cross-validation as well as blind test data uses n-gram features with bidirectional long short-term memory.

Tobias Strauß, Max Weidemann, Johannes Michael et al.

We present a recognition and retrieval system for the ICDAR2017 Competition on Information Extraction in Historical Handwritten Records which successfully infers person names and other data from marriage records. The system extracts information from the line images with a high accuracy and outperforms the baseline. The optical model is based on Neural Networks. To infer the desired information, regular expressions are used to describe the set of feasible words sequences.