Abstract | ||
---|---|---|
In this paper, an approach based on lacunarity to locate address blocks in postal envelopes is proposed. After computing the lacunarity of a postal envelope image, a non-linear transformation is applied on it. A thresholding technique is then used to generate evidences. Finally, a region growing is applied to reconstruct semantic objects like stamps, postmarks, and address blocks. Very little a priori knowledge of the envelope images is required. By using the lacunarity for several ranges of neighbor window sizes r onto 200 postal envelope images, the proposed approach reached a success rate over than 97% on average. |
Year | DOI | Venue |
---|---|---|
2005 | 10.1007/11578079_12 | CIARP |
Keywords | Field | DocType |
texture measure,non-linear transformation,neighbor window sizes r,postal envelope image,semantic object,postal envelope,envelope image,success rate,address block segmentation,region growing,address block,a priori knowledge,linear transformation | Computer vision,Pattern recognition,Computer science,Segmentation,A priori and a posteriori,Image processing,Sierpinski carpet,Artificial intelligence,Region growing,Thresholding,Lacunarity | Conference |
Volume | ISSN | ISBN |
3773 | 0302-9743 | 3-540-29850-9 |
Citations | PageRank | References |
4 | 0.43 | 4 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jacques Facon | 1 | 67 | 15.67 |
David Menoti | 2 | 13 | 1.44 |
Arnaldo de Albuquerque Araújo | 3 | 479 | 34.55 |