Sciweavers

196 search results - page 15 / 40
» Text detection in natural scene images with feature combinat...
Sort
View
MIR
2004
ACM
105views Multimedia» more  MIR 2004»
15 years 3 months ago
Image recognition for digital libraries
The interpretation of natural scenes, generally so obvious and effortless for humans, still remains a challenge in computer vision. To allow the search of image-based documents i...
Bertrand Le Saux, Giuseppe Amato
ICMCS
2010
IEEE
149views Multimedia» more  ICMCS 2010»
14 years 10 months ago
Single-view recaptured image detection based on physics-based features
In daily life, we can see images of real-life objects on posters, television, or virtually any type of smooth physical surfaces. We seldom confuse these images with the objects pe...
Xinting Gao, Tian-Tsong Ng, Bo Qiu, Shih-Fu Chang
CVPR
2005
IEEE
15 years 12 months ago
Pedestrian Detection in Crowded Scenes
In this paper, we address the problem of detecting pedestrians in crowded real-world scenes with severe overlaps. Our basic premise is that this problem is too difficult for any t...
Bastian Leibe, Edgar Seemann, Bernt Schiele
CIVR
2009
Springer
221views Image Analysis» more  CIVR 2009»
15 years 4 months ago
Movie segmentation into scenes and chapters using locally weighted bag of visual words
Movies segmentation into semantically correlated units is a quite tedious task due to ”semantic gap”. Low-level features do not provide useful information about the semantical...
Vasileios Chasanis, Argyris Kalogeratos, Aristidis...
TCSV
2002
292views more  TCSV 2002»
14 years 9 months ago
Document image segmentation using wavelet scale-space features
In this paper, an efficient and computationally fast method for segmenting text and graphics part of document images based on textural cues is presented. We assume that the graphic...
Mausumi Acharyya, Malay K. Kundu