Sciweavers

244 search results - page 44 / 49
» A New Fingerprinting Method For Digital Images
Sort
View
ICDAR
2003
IEEE
14 years 27 days ago
Best Practices for Convolutional Neural Networks Applied to Visual Document Analysis
Neural networks are a powerful technology for classification of visual inputs arising from documents. However, there is a confusing plethora of different neural network methods th...
Patrice Simard, David Steinkraus, John C. Platt
CVPR
2010
IEEE
14 years 4 months ago
Boundary Learning by Optimization with Topological Constraints
Recent studies have shown that machine learning can improve the accuracy of detecting object boundaries in images. In the standard approach, a boundary detector is trained by mini...
Viren Jain, Benjamin Bollmann, Bobby Kasthuri, Ken...
ISVC
2009
Springer
14 years 2 months ago
Animated Classic Mosaics from Video
Generating artificial classic mosaics from digital images is an area of NPR rendering that has recently seen several successful approaches. A sequence of mosaic images creates a u...
Yu Liu, Olga Veksler
ICDAR
2011
IEEE
12 years 7 months ago
Aletheia - An Advanced Document Layout and Text Ground-Truthing System for Production Environments
- Large-scale digitisation has led to a number of new possibilities with regard to adaptive and learning based methods in the field of Document Image Analysis and OCR. For ground t...
C. Clausner, Stefan Pletschacher, Apostolos Antona...

Publication
197views
12 years 3 months ago
Convex non-negative matrix factorization for massive datasets
Non-negative matrix factorization (NMF) has become a standard tool in data mining, information retrieval, and signal processing. It is used to factorize a non-negative data matrix ...
C. Thurau, K. Kersting, M. Wahabzada, and C. Bauck...