Výsledky vyhledávání - "Koelsch, Andreas"

Report

Recognizing Challenging Handwritten Annotations with Fully Convolutional Networks

Autor: Kölsch, Andreas, Mishra, Ashutosh, Varshneya, Saurabh, Afzal, Muhammad Zeshan, Liwicki, Marcus

Publikováno v: 16th International Conference on Frontiers in Handwriting Recognition 2018

This paper introduces a very challenging dataset of historic German documents and evaluates Fully Convolutional Neural Network (FCNN) based methods to locate handwritten annotations of any kind in these documents. The handwritten annotations can appe

Externí odkaz: http://arxiv.org/abs/1804.00236

Zobrazit plný text záznamu

Report

Real-Time Document Image Classification using Deep CNN and Extreme Learning Machines

Autor: Kölsch, Andreas, Afzal, Muhammad Zeshan, Ebbecke, Markus, Liwicki, Marcus

This paper presents an approach for real-time training and testing for document image classification. In production environments, it is crucial to perform accurate and (time-)efficient training. Existing deep learning approaches for classifying docum

Externí odkaz: http://arxiv.org/abs/1711.05862

Zobrazit plný text záznamu

Report

Cutting the Error by Half: Investigation of Very Deep CNN and Advanced Training Strategies for Document Image Classification

Autor: Afzal, Muhammad Zeshan, Kölsch, Andreas, Ahmed, Sheraz, Liwicki, Marcus

We present an exhaustive investigation of recent Deep Learning architectures, algorithms, and strategies for the task of document image classification to finally reduce the error by more than half. Existing approaches, such as the DeepDocClassifier,

Externí odkaz: http://arxiv.org/abs/1704.03557

Zobrazit plný text záznamu

Report

Multilevel Context Representation for Improving Object Recognition

Autor: Kölsch, Andreas, Afzal, Muhammad Zeshan, Liwicki, Marcus

In this work, we propose the combined usage of low- and high-level blocks of convolutional neural networks (CNNs) for improving object recognition. While recent research focused on either propagating the context from all layers, e.g. ResNet, (includi

Externí odkaz: http://arxiv.org/abs/1703.06408

Zobrazit plný text záznamu

Akademický článek

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Akademický článek

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Introducing Simple Detection of Bioavailable Arsenic at Rafaela (Santa Fe Province, Argentina) Using the ARSOlux Biosensor

Autor: Siegfried, Konrad, Hahn Tomer, Sonja, Koelsch, Andreas, Osterwalder, Eva, Mattusch, Juergen, Staerk, Hans Joachim, Meichtry, Jorge Martin, De Seta, Graciela E., Reina, Fernando D., Panigatti, Maria Cecilia, Litter, Marta Irene, Harms, Hauke

Publikováno v: International Journal of Environmental Research and Public Health, Vol 12, Iss 5, Pp 5465-5482 (2015)
CONICET Digital (CONICET)
Consejo Nacional de Investigaciones Científicas y Técnicas
instacron:CONICET
International Journal of Environmental Research and Public Health
Volume 12
Issue 5
Pages 5465-5482

Numerous articles have reported the occurrence of arsenic in drinking water in Argentina, and the resulting health effects in severely affected regions of the country. Arsenic in drinking water in Argentina is largely naturally occurring due to eleva

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=pmid_dedup__::eea9e333a4247e3844800012981de58d
http://www.mdpi.com/1660-4601/12/5/5465

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání