| 摘要 |
A computer-implemented method of font identification includes receiving a first document, the first document including the first text set in a proportional font. Test text, corresponding to the first text of the first document, is received. The test text is set in a test font. A first fingerprint is generated, based on relative line widths of the first text of the first document. A second fingerprint is generated based on relative line widths of the test text, as set in the test font. The test font is then accepted as being consistent with a font of the first text, based on a predetermined strength of relationship between the first and second fingerprints.
|
