Sciweavers

2632 search results - page 290 / 527
» Analysis of whole-book recognition
Sort
View
DRR
2009
15 years 4 months ago
Retrieval of historical documents by word spotting
The implementation of word spotting is not an easy procedure and it gets even worse in the case of historical documents since it requires character recognition and indexing of the...
Nikoleta Doulgeri, Ergina Kavallieratou
ICDAR
2009
IEEE
15 years 4 months ago
Extraction of Characters on Signboards in Natural Scene Images by Stump Classifiers
We present a method to detect characters on signboards in natural scene images. For many applications, both classifier with small computational cost and the efficient feature set,...
Minoru Maruyama, Takuma Yamaguchi
ICDAR
2009
IEEE
15 years 4 months ago
Coupled Snakelet Model for Curled Textline Segmentation of Camera-Captured Document Images
Detection of curled textline is important for dewarping of hand-held camera-captured document images. Then baselines and the lines following the top of x-height of characters (x-l...
Syed Saqib Bukhari, Faisal Shafait, Thomas M. Breu...
ICIAR
2009
Springer
15 years 4 months ago
Invariant Shape Matching for Detection of Semi-local Image Structures
Abstract. Shape features applied to object recognition has been actively studied since the beginning of the field in 1950s and remain a viable alternative to appearance based metho...
Lech Szumilas, Horst Wildenauer, Allan Hanbury
ICASSP
2011
IEEE
14 years 10 months ago
Robust speaker identification using a CASA front-end
Speaker recognition remains a challenging task under noisy conditions. Inspired by auditory perception, computational auditory scene analysis (CASA) typically segregates speech by...
Xiaojia Zhao, Yang Shao, DeLiang Wang