810 search results - page 11 / 162 » Learning to Segment Document Images |
CVPR
2006
IEEE
15 years 11 months ago
2006
IEEE
Image segmentation is a fundamental step in many computer vision applications. Generally, the choice of a segmentation algorithm, or parameterization of a given algorithm, is sele...
86
Voted
PAMI
2002
14 years 9 months ago
2002
: We propose a method for text retrieval from document images without the use of OCR. Documents are segmented into character objects. Image features, namely the Vertical Traverse D...
ICIP
2007
IEEE
15 years 11 months ago
2007
IEEE
In this paper we explore H.264/AVC operating in intraframe mode to compress a mixed image, i.e. composed of text, graphics and pictures. Even though mixed contents (compound) docu...
ICDAR
1999
IEEE
15 years 1 months ago
1999
IEEE
PixED (from Pixel to Electronic Document) is aimed at converting document images into structured electronic documents which can be read by a machine for information retrieval. The...
88
Voted
ICPR
2000
IEEE
15 years 10 months ago
2000
IEEE
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...