Supervisor: Michael Reiter Background Flow Cytometry is a laser-based technique to measure antigen expression levels of blood cells. It is used in research as well as in daily clinical routines for immunophenotyping and for monitoring residual numbers of cancer cells during chemotherapy. One patient’s sample contains approximately 50-300k cells (also called events) with up to … Continue reading Designing efficient Data Augmentation Strategies for Flow Cytometry Data →
Supervisors: Michael Reiter, Matthias Wödlinger, Florian Kowarsch Background Flow Cytometry is a laser-based technique to measure antigen expression levels of blood cells. It is used in research as well as in daily clinical routines for immunophenotyping and for monitoring residual numbers of cancer cells during chemotherapy. One patient’s sample contains approximately 50-300k cells (also called … Continue reading Multi-step classification of flow cytometry cell data with set transformers →
Supervisor: Michael Reiter, Florian Kowarsch Background Flow Cytometry is a laser-based technique to measure antigen expression levels of blood cells. It is used in research as well as in daily clinical routines for immunophenotyping and for monitoring residual numbers of cancer cells during chemotherapy. One patient’s sample contains approximately 50-300k cells (also called events) with … Continue reading CNN based classification of Flow Cytometry Data →
Anmeldung via TISS. Erstbesprechung: 2. März 09:00 mit der VO Übungsablauf TeilnehmerInnen lösen individuelle Aufgaben. Es gibt keinen regelmäßigen Übungstermin, der LVA-Leiter steht aber für individuelle Terminvereinbarungen zur Verfügung (Beantwortung von Fragen, allgemeine Beratung, Besprechung des Programm-Codes usw.). Es gibt jedoch einen Termin zur Präsentation der Aufgabenstellung, einen Termin zur Zwischenpräsentation und einen für die … Continue reading Scene Understanding and Surveillance (UE) →
Vorlesung: Mittwoch, 1. 3.2023, 09.00-10.00 Uhr c.t. (Vormals: Video Analysis) Ort: Seminarraum FAV 01 A (Seminarraum 183/2) Beginn: 1.3.2023 (Vorbesprechung der VO und LU) Weitere Informationen: TISS und TUWEL In dieser LVA wird die Analyse von Bildfolgen (Videos, Tiefen- und Thermaldaten) vertiefend behandelt: dazu gehören die Themengebiete Sensorik, Bewegungserkennung, Objektverfolgung, Szenen-Rekonstruktion und Performance Evaluation. Fragestellungen … Continue reading Scene Understanding and Surveillance →
The enhancement of document images describes the task of improving the visual quality of document images. Thus, degradations (like background clutter or uneven illumination) can be removed. Enhancement can be used as a preprocessing step for further document image analysis methods – including text recognition. Goal The aim of this internship is to select an … Continue reading Document image enhancement →
An often used preprocessing step in text recognition systems is text line detection. The aim of this internship is to implement an existing method for text line detection. Goal Implement an existing method, which is introduced in [1]. Compare the results of your implementation with results gained in the original work. Workflow Literature review Data … Continue reading Text Line Detection →
Offline Handwritten Text Recognition (HTR) describes the task of transcribing handwritten text into digital texts. Compared to Optical Character Recognition (OCR), HTR is much more challenging and still an open problem.Recently, a transformer based framework named TrOCR was suggested in [1]. Goal The aim of this internship is to fine-tune existing HTR models in [1] … Continue reading Handwritten Text Recognition →
Supervisor: Fabian Hollaus The quality of photographs of single document pages or book pages is often limited by distortions. Dewarping techniques can be used in order to remove such distortions, i.e. rectify the document images. Goal The aim of this work is to implement a document image dewarping algorithm. The method should make use of … Continue reading Document Dewarping →
Status: available Supervisors: Michael Reiter, Matthias Wödlinger Why? The target dataset is the enormous digitised collection of historical printed publications at Austrian National Library. In particular, Austrian Books Online (digitised over the last years in a large-scale cooperation with Google) and Austrian Newspapers Online from 16th to 19th century, which rank among the most important … Continue reading Document image classification of historic book pages →
