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
A system that learns to tag videos by watching youtube
TL;DR: A system that automatically tags videos, i.e. detects high-level semantic concepts like objects or actions in them, that uses videos from online portals like youtube.com as a novel source of training data, whereas tags provided by users during upload serve as ground truth annotations, to learn autonomously by automatically downloading its training set.
Book
Geometric Aspects of Visual Object Recognition
TL;DR: A recognition algorithm (RAST) that works efficiently even when no correspondence or grouping information is given; that is, it works in the presence of large amounts of clutter and with very primitive features form the basis for a simple, efficient, and robust approach to the geometric aspects of 3D object recognition from 2D image.
Proceedings ArticleDOI
Can we build language-independent OCR using LSTM networks?
Adnan Ul-Hasan,Thomas M. Breuel +1 more
TL;DR: The question to what extent LSTM models can be used for multilingual OCR without the use of language models is explored, and cross-language performance of L STM models trained on different languages is measured.
Proceedings ArticleDOI
Layout Analysis of Urdu Document Images
TL;DR: A layout analysis system for extracting text-lines in reading order from Urdu document images shows high text-line detection accuracy on scanned images of Urdu prose and poetry books and magazines and works reasonably well on newspaper images.
Proceedings ArticleDOI
Anomaly detection by combining decision trees and parametric densities
TL;DR: The proposed method combines the advantages of classification trees with the benefit of a more accurate representation of the outliers, which yields to more precise decision boundaries and a deterministic classification result.