Abstract | ||
---|---|---|
We present a method for off-line reading of cursive handwriting, which derives from modelling handwriting as a complex movement. The method includes a step for recovering the writing order from static images of handwriting, a segmentation algorithm that decomposes the “unfolded” ink into strokes, an ink matching step to compare the ink of the unknown handwriting with those of a set of reference words, of whom the transcripts are given, and a graph search algorithm to search for the best interpretation among the possible ones. The method does not involve any feature extraction, nor a classification stage and may benefit from a linguistic context, if available. We report the results of experiments on 8,000 samples, draw some conclusions and outline further developments. |
Year | DOI | Venue |
---|---|---|
2010 | 10.1109/ICFHR.2010.21 | ICFHR |
Keywords | Field | DocType |
cursive handwriting,segmentation algorithm,modelling handwriting,linguistic context,feature extraction,complex movement,graph search algorithm,unknown handwriting,best interpretation,classification stage,labeling,handwriting recognition,graph theory,ink,image segmentation,dictionaries,shape | Graph theory,Graph traversal,Handwriting,Pattern recognition,Computer science,Segmentation,Handwriting recognition,Feature extraction,Image segmentation,Artificial intelligence,Word processing | Conference |
Citations | PageRank | References |
0 | 0.34 | 9 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Claudio De Stefano | 1 | 158 | 32.68 |
Angelo Marcelli | 2 | 139 | 32.42 |
Antonio Parziale | 3 | 25 | 5.66 |
Rosa Senatore | 4 | 13 | 2.89 |