Sciweavers

1144 search results - page 27 / 229
» Energy-Based Models in Document Recognition and Computer Vis...
Sort
View
CVPR
2007
IEEE
15 years 11 months ago
Probabilistic Reverse Annotation for Large Scale Image Retrieval
Automatic annotation is an elegant alternative to explicit recognition in images. In annotation, the image is matched with keyword models, and the most relevant keywords are assig...
K. Pramod Sankar, C. V. Jawahar
CVPR
2004
IEEE
15 years 11 months ago
Restoration of Curved Document Images through 3D Shape Modeling
In this paper, we address the problem of discovering the 3D shape of a book surface from the shading information in a scanned document image. This shapefrom-shading problem is cha...
Zheng Zhang 0003, Chew Lim Tan, Liying Fan
ICPR
2000
IEEE
15 years 10 months ago
Extraction of Relevant Information from Document Images Using Measures of Visual Attention
This paper describes an approach to attention based layout segmentation using general principles of the human visual perception to achieve this goal. The text is considered as tex...
Gerd Maderlechner, Angela Schreyer, Peter Suda
ICPR
2010
IEEE
14 years 7 months ago
Exploiting Combined Multi-level Model for Document Sentiment Analysis
This paper focuses on the task of text sentiment analysis in hybrid online articles and web pages. Traditional approaches of text sentiment analysis typically work at a particular ...
Si Li, Hao Zhang, Weiran Xu, Guang Chen, Jun Guo
ICPR
2008
IEEE
15 years 11 months ago
Structural poisson mixtures for classification of documents
Considering the statistical text classification problem we approximate class-conditional probability distributions by structurally modified Poisson mixtures. By introducing the st...
Jana Novovicová, Jiri Grim, Petr Somol