1.   An ulterior motive for performing text recognition is to convert existing printed material into a computer format that permits further processing.

2.   Analogously, computerised text recognition needs to use higher level knowledge to achieve comparable levels of performance.

3.   Existing systems for performing text recognition are susceptible to errors.

4.   It has been shown to make a significant contribution to text recognition, and the results are described in Chapter Three.

5.   The techniques are more generally applicable to all areas of text recognition.

6.   There are difficulties associated with automatic text recognition however.

7.   Three approaches are generally considered for the application of contextual information in the field of text recognition.

n. + recognition >>共 128
name 42.46%
speech 9.81%
brand 7.33%
voice 6.57%
handwriting 2.80%
face 2.37%
pattern 2.16%
word 1.94%
government 1.51%
brand-name 1.08%
text 0.75%
text + n. >>共 167
message 20.72%
file 11.26%
book 7.01%
editor 3.92%
document 3.75%
box 2.61%
pager 1.63%
form 1.47%
panel 1.31%
recognition 1.14%
每页显示:    共 7