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
Posted Content
On the Relationship between the Posterior and Optimal Similarity
TL;DR: The paper first shows that it can reconstruct, up to class labels, the class posterior distribution, and gives an asymptotically Bayes-optimal classification procedure, and analyzes Bayesian similarity in a framework where a classifier faces a number of related classification tasks (multitask learning).
Book ChapterDOI
Towards Searchable Line Drawings, a Content-Based Symbol Retrieval Approach with Variable Query Complexity
TL;DR: An approach for focused symbol retrieval as step towards achieving the goal of both high accuracy and efficiency on large databases of line drawings is presented by using concepts from image retrieval.
Patent
Systeme et procede de recherche et de recommandation de documents dans une collection a l'aide de signets partages
TL;DR: In this paper, a systeme de recherches et de recommandations fonctionne dans le contexte d'un gestionnaire de signets partages, which memorise les signets des utilisateurs individuels (dont certains peuvent etre publies ou partages pour l'utilisation du groupe) sur a base de donnees de signet centralisee connectee a Internet.
Patent
Method for operating on vertical surface
TL;DR: In this paper, a method for operating a white board printer capable of executing various mechanical works is presented, where a forming sealing element or end effecter 130 for working on a substantially vertical surface is held at or moved to its place by an effecter base 120.
Posted Content
Learning Similarity for Character Recognition and 3D Object Recognition
TL;DR: An approach to similarity motivated byBayesian methods yields a similarity function that is learnable using a standard Bayesian methods and Experimental results on character recognition and 3D object recognition are presented.