Sciweavers

3716 search results - page 614 / 744
» On the monotonization of the training set
Sort
View
CVPR
2008
IEEE
15 years 8 months ago
Learning-based face hallucination in DCT domain
In this paper, we propose a novel learning-based face hallucination framework built in DCT domain, which can recover the high-resolution face image from a single lowresolution one...
Wei Zhang, Wai-kuen Cham
DAS
2008
Springer
15 years 8 months ago
A Complete Optical Character Recognition Methodology for Historical Documents
In this paper a complete OCR methodology for recognizing historical documents, either printed or handwritten without any knowledge of the font, is presented. This methodology cons...
Georgios Vamvakas, Basilios Gatos, Nikolaos Stamat...
DAS
2008
Springer
15 years 8 months ago
Super-Resolution of Text Images Using Edge-Directed Tangent Field
This paper presents an edge-directed super-resolution algorithm for gray level document images without using any training set. This technique creates an image with smooth regions ...
Jyotirmoy Banerjee, C. V. Jawahar
ECOOP
2008
Springer
15 years 8 months ago
Online Phase-Adaptive Data Layout Selection
Good data layouts improve cache and TLB performance of object-oriented software, but unfortunately, selecting an optimal data layout a priori is NP-hard. This paper introduces layo...
Chengliang Zhang, Martin Hirzel
AI
2010
Springer
15 years 8 months ago
Improving Multiclass Text Classification with Error-Correcting Output Coding and Sub-class Partitions
Error-Correcting Output Coding (ECOC) is a general framework for multiclass text classification with a set of binary classifiers. It can not only help a binary classifier solve mul...
Baoli Li, Carl Vogel