Abstract | ||
---|---|---|
In this paper, a process of expansion of the training set by synthetic generation of handwritten uppercase letters via deformations of natural images is tested in combination with an approximate k-Nearest Neighbor (k-NN) classifier. It has been previously shown [11] [10] that approximate nearest neighbors search in large databases can be successfully used in an OCR task, and that significant performance improvements can be consistently obtained by simply increasing the size of the training set. In this work, extensive experiments adding distorted characters to the training set are performed, and the results are compared to directly adding new natural samples to the set of prototypes. |
Year | DOI | Venue |
---|---|---|
2002 | 10.1007/3-540-70659-3_57 | SSPR/SPR |
Keywords | Field | DocType |
handwritten character recognition,new natural sample,approximate k-nearest,training set,large databases,distorted character,training set expansion,handwritten uppercase letter,ocr task,approximate nearest neighbors search,natural image,extensive experiment,k nearest neighbor | Training set,Nearest neighbour,Pattern recognition,Character recognition,Computer science,Optical character recognition,Speech recognition,Artificial intelligence,Classifier (linguistics) | Conference |
ISBN | Citations | PageRank |
3-540-44011-9 | 19 | 1.29 |
References | Authors | |
13 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Javier Cano | 1 | 65 | 12.20 |
Juan C. Pérez-Cortés | 2 | 137 | 16.20 |
Joaquim Arlandis | 3 | 85 | 9.92 |
Rafael Llobet | 4 | 72 | 8.78 |