Abstract | ||
---|---|---|
This article describes a new segmentation bythresholding approach based on learning. The methodconsists in learning to threshold correctly submitting bothan image and its ideal thresholded version. From thisstage it is generated a decision matrix for each pixel andeach gray level that is re-utilized at the moment of thenew images segmentation. The new image is thresholdedby means of a new strategy based on the nearestneighbors, that seeks, for each pixel of this new image,the best solution in the decision matrix. Performed testson handwritten documents showed promising results. Interms of quality of the results, the developed technique isequal or superior to the traditional segmentation bythresholding techniques, with the advantage that the onediscussed here does not requires the use of heuristicparameters. |
Year | DOI | Venue |
---|---|---|
2003 | 10.1109/ICDAR.2003.1227776 | ICDAR-1 |
Keywords | Field | DocType |
image segmentation,decision matrix,best solution,performed testson handwritten document,new strategy,thenew images segmentation,new segmentation,new image,learning approach,pixel andeach gray level,traditional segmentation,bothan image,genetic algorithms,nearest neighbor,testing,lighting,image processing,neural networks,pixel,informatics | Computer vision,Scale-space segmentation,Decision matrix,Pattern recognition,Image texture,Segmentation,Computer science,Segmentation-based object categorization,Image processing,Image segmentation,Region growing,Artificial intelligence | Conference |
ISSN | ISBN | Citations |
1520-5363 | 0-7695-1960-1 | 0 |
PageRank | References | Authors |
0.34 | 4 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Horacio Legal-Ayala | 1 | 8 | 2.93 |
Jacques Facon | 2 | 67 | 15.67 |
Legal-Ayala, H.A. | 3 | 0 | 0.34 |