T
Thomas M. Breuel
Researcher at Nvidia
Publications - 240
Citations - 10811
Thomas M. Breuel is an academic researcher from Nvidia. The author has contributed to research in topics: Optical character recognition & Image segmentation. The author has an hindex of 43, co-authored 237 publications receiving 9547 citations. Previous affiliations of Thomas M. Breuel include Google & Xerox.
Papers
More filters
Book ChapterDOI
Automatic image tagging using community-driven online image databases
TL;DR: This work analyzes image sets taken from online community-driven image databases, such as Flickr, for use in concept identification and real-world performance is measured using the flexible tagging system, Tagr.
Proceedings ArticleDOI
Recognizable units in Pashto language for OCR
Riaz Ahmad,Muhammad Zeshan Afzal,Sheikh Faisal Rashid,Marcus Liwicki,Andreas Dengel,Thomas M. Breuel +5 more
TL;DR: The objective of this work is to find out the alternate recognizable units in Pashto cursive script, including ligatures and primary ligatures, which represent the basic shapes of all the ligatures.
Book ChapterDOI
On the use of geometric matching for both: isolated symbol recognition and symbol spotting
Nibal Nayef,Thomas M. Breuel +1 more
TL;DR: This paper presents the use of geometric matching for symbol recognition under similarity transformations and incorporates this matching approach in a complete symbol recognition/spotting system, which consists of denoising, symbol representation and recognition.
Proceedings ArticleDOI
Statistical Grouping for Segmenting Symbols Parts from Line Drawings, with Application to Symbol Spotting
Nibal Nayef,Thomas M. Breuel +1 more
TL;DR: The use of statistical grouping for partitioning line drawings into shapes, those shapes represent meaningful parts of the symbols that constitute the line drawings, making isolated recognition methods applicable for spotting symbols in context and making them perform faster and more accurately.
Posted Content
Discovering Nonlinear Relations with Minimum Predictive Information Regularization.
TL;DR: This work introduces a novel minimum predictive information regularization method to infer directional relations from time series, allowing deep learning models to discover nonlinear relations.