Abstract | ||
---|---|---|
This paper presents a complete procedure for the segmentation of handwritten numeric strings. The procedure uses an hypothesis-then-verification strategy in which multiple segmentation algorithms based on contiguous row partition work sequentially on the binary image until an acceptable segmentation is obtained. At this purpose a new set of algorithms simulating a “drop falling” process is introduced. The experimental tests demonstrate the effectiveness of the new algorithms in obtaining high-confidence segmentation hypotheses |
Year | DOI | Venue |
---|---|---|
1995 | 10.1109/ICDAR.1995.602080 | Document Analysis and Recognition, 1995., Proceedings of the Third International Conference |
Keywords | Field | DocType |
character recognition,image segmentation,handwritten numeric strings,high-confidence segmentation hypotheses,hypothesis-then-verification strategy,multiple segmentation algorithms,numeric strings segmentation | Computer vision,Scale-space segmentation,Pattern recognition,Character recognition,Segmentation,Computer science,Binary image,Segmentation-based object categorization,Image segmentation,Artificial intelligence,Minimum spanning tree-based segmentation | Conference |
Volume | ISBN | Citations |
2 | 0-8186-7128-9 | 29 |
PageRank | References | Authors |
1.77 | 3 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
G. Congedo | 1 | 42 | 3.62 |
G. Dimauro | 2 | 33 | 3.97 |
S. Impedovo | 3 | 369 | 31.83 |
G. Pirlo | 4 | 552 | 39.16 |