Title | ||
---|---|---|
A holistic classification system for check amounts based on neural networks with rejection |
Abstract | ||
---|---|---|
A holistic classification system for off-line recognition of legal amounts in checks is described in this paper. The binary images obtained from the cursive words are processed following the human visual system, employing a Hough transform method to extract perceptual features. Images are finally coded into a bidimensional feature map representation. Multilayer perpeptrons are used to classify these feature maps into one of the 32 classes belonging to the CENPARMI database. To select a final classification system, ROC graphs are used to fix the best threshold values of the classifiers to obtain the best tradeoff between accuracy and misclassification. |
Year | DOI | Venue |
---|---|---|
2005 | 10.1007/11590316_45 | PReMI |
Keywords | Field | DocType |
multilayer perpeptrons,perceptual feature,final classification system,neural network,bidimensional feature map representation,best tradeoff,best threshold value,holistic classification system,feature map,human visual system,cenparmi database,binary image,classification system,hough transform | Graph,Cursive,Pattern recognition,Human visual system model,Computer science,Binary image,Hough transform,Handwriting recognition,Artificial intelligence,Artificial neural network | Conference |
Volume | ISSN | ISBN |
3776 | 0302-9743 | 3-540-30506-8 |
Citations | PageRank | References |
1 | 0.36 | 4 |
Authors | ||
10 |
Name | Order | Citations | PageRank |
---|---|---|---|
M. J. Castro | 1 | 37 | 5.96 |
W. Díaz | 2 | 1 | 0.36 |
F J. Ferri | 3 | 293 | 22.43 |
José Ruiz-Pinales | 4 | 28 | 8.35 |
R. Jaime-Rivas | 5 | 23 | 3.13 |
fernando blat | 6 | 2 | 1.39 |
S. España | 7 | 1 | 0.36 |
P. Aibar | 8 | 7 | 1.16 |
S. Grau | 9 | 1 | 0.36 |
D. Griol | 10 | 2 | 1.06 |