Abstract | ||
---|---|---|
The lower the resolution of a given text is, the more dif- ficult it becomes to segment it into single characters. The resolution of screen-rendered text can be very low. This pa- per focuses on smoothed screen-rendered text of very low resolution with typical x-heights of 4 to 7 pixels which is much lower than in other low resolution OCR situations. We propose a recognition-based segmentation algorithm which makes use of oversegmentation by dynamic programming, candidate rating by single character classifiers and a graph based search algorithm for an optimal cut sequence. The al- gorithm is described in detail and experimental results are presented which show the performance on example screen- shot images taken from the public Screen-Word database. |
Year | DOI | Venue |
---|---|---|
2007 | 10.1109/ICDAR.2007.229 | ICDAR-1 |
Keywords | Field | DocType |
low resolution,low resolution screen-rendered text,single character,example screen,candidate rating,search algorithm,low resolution ocr situation,screen-rendered text,recognition-based segmentation algorithm,dynamic programming,single character classifier,image resolution,graph theory,image classification,image segmentation,text analysis | Graph theory,Computer vision,Dynamic programming,Search algorithm,Pattern recognition,Computer science,Segmentation,Image segmentation,Artificial intelligence,Pixel,Contextual image classification,Image resolution | Conference |
ISBN | Citations | PageRank |
0-7695-2822-8 | 3 | 0.46 |
References | Authors | |
3 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
S. Wachenfeld | 1 | 3 | 0.46 |
S. Fleischer | 2 | 3 | 0.46 |
H.-U. Klein | 3 | 3 | 0.46 |
X. Jiang | 4 | 13 | 1.70 |