Paper Info
Title
Segmentation of Postal Envelopes for Address Block Location: an approach based on feature selection in wavelet space
Abstract
This paper presents a segmentation algorithm basedon feature selection in wavelet space. The aim is toautomatically separate in postal envelopes the regionsrelated to background, stamps, rubber stamps, and theaddress blocks. First, a typical image of a postalenvelope is decomposed using Mallat algorithm and Haarbasis. High frequency channel outputs are analyzed tolocate salient points in order to separate the background.A statistical hypothesis test is taken to decide upon moreconsistent regions in order to clean out some noise left.The selected points are projected back to the originalgray level image, where the evidence from the waveletspace is used to start a growing process to include thepixels more likely to belong to the regions of stamps,rubber stamps, and written area. Experiments are runusing original postal envelopes from the Brazilian PostOffice Agency, and here we report results on 440 imageswith many different layouts and backgrounds.
Year
DOI
Venue
2003
10.1109/ICDAR.2003.1227752
ICDAR-1
Keywords
Field
DocType
frequency,feature selection,informatics,hidden markov models,testing,high frequency,hypothesis test,rubber,image segmentation
Computer vision,Pattern recognition,Feature selection,Computer science,Segmentation,Communication channel,Image segmentation,Artificial intelligence,Hidden Markov model,Statistical hypothesis testing,Salient,Wavelet
Conference
ISSN
ISBN
Citations 
1520-5363
0-7695-1960-1
7
PageRank 
References 
Authors
0.53
8
4
Name
Order
Citations
PageRank
David Menoti1131.44
Díbio Leandro Borges2589.61
Jacques Facon36715.67
Alceu De Souza Britto, Jr.420012.91