Paper Abstract and Keywords |
Presentation |
2004-09-16 14:20
Calculation of a Threshold Value for a Character Recognition System Oscar Vanegas (MEW) |
Abstract |
(in Japanese) |
(See Japanese page) |
(in English) |
In general, an ideal character recognition system must be able to find characters on a selected region of interest even having high variability of intensities, large amount of noise, bad contrast etc.. However these adverse conditions make very difficult the process of finding the best threshold value for separation. Several methods have been proposed so far, in order to find the best threshold value. Some methods are based on the maximization of the separability of the resultant classes in gray levels. Other methods are based on the estimation of free parameters on a training set of images which are used during testing. Others, rely on binary images for text detection.
This paper proposes a method in order to calculate a range in which the threshold value can be located, able to produce the best results for character recognition when an adverse condition is present. In the proposed method, the image is first segmented into several objects. The contrast of each object is calculated by analyzing relations with consecutive objects. After applying this method, objects which belong to the foreground can be obtained. The proposed method does not need to have any previous training set and can be used easily with any type of data. |
Keyword |
(in Japanese) |
(See Japanese page) |
(in English) |
Threshold Value / Image Segmentation / Character Recognition / / / / / |
Reference Info. |
IEICE Tech. Rep., vol. 104, no. 301, IT2004-33, pp. 11-14, Sept. 2004. |
Paper # |
IT2004-33 |
Date of Issue |
2004-09-09 (IT) |
ISSN |
Print edition: ISSN 0913-5685 |
Download PDF |
|
Conference Information |
Committee |
IT |
Conference Date |
2004-09-16 - 2004-09-17 |
Place (in Japanese) |
(See Japanese page) |
Place (in English) |
Osaka Sangyo Univ. |
Topics (in Japanese) |
(See Japanese page) |
Topics (in English) |
general |
Paper Information |
Registration To |
IT |
Conference Code |
2004-09-IT |
Language |
English |
Title (in Japanese) |
(See Japanese page) |
Sub Title (in Japanese) |
(See Japanese page) |
Title (in English) |
Calculation of a Threshold Value for a Character Recognition System |
Sub Title (in English) |
|
Keyword(1) |
Threshold Value |
Keyword(2) |
Image Segmentation |
Keyword(3) |
Character Recognition |
Keyword(4) |
|
Keyword(5) |
|
Keyword(6) |
|
Keyword(7) |
|
Keyword(8) |
|
1st Author's Name |
Oscar Vanegas |
1st Author's Affiliation |
Matsushita Denko (MEW) |
2nd Author's Name |
|
2nd Author's Affiliation |
() |
3rd Author's Name |
|
3rd Author's Affiliation |
() |
4th Author's Name |
|
4th Author's Affiliation |
() |
5th Author's Name |
|
5th Author's Affiliation |
() |
6th Author's Name |
|
6th Author's Affiliation |
() |
7th Author's Name |
|
7th Author's Affiliation |
() |
8th Author's Name |
|
8th Author's Affiliation |
() |
9th Author's Name |
|
9th Author's Affiliation |
() |
10th Author's Name |
|
10th Author's Affiliation |
() |
11th Author's Name |
|
11th Author's Affiliation |
() |
12th Author's Name |
|
12th Author's Affiliation |
() |
13th Author's Name |
|
13th Author's Affiliation |
() |
14th Author's Name |
|
14th Author's Affiliation |
() |
15th Author's Name |
|
15th Author's Affiliation |
() |
16th Author's Name |
|
16th Author's Affiliation |
() |
17th Author's Name |
|
17th Author's Affiliation |
() |
18th Author's Name |
|
18th Author's Affiliation |
() |
19th Author's Name |
|
19th Author's Affiliation |
() |
20th Author's Name |
|
20th Author's Affiliation |
() |
Speaker |
Author-1 |
Date Time |
2004-09-16 14:20:00 |
Presentation Time |
25 minutes |
Registration for |
IT |
Paper # |
IT2004-33 |
Volume (vol) |
vol.104 |
Number (no) |
no.301 |
Page |
pp.11-14 |
#Pages |
4 |
Date of Issue |
2004-09-09 (IT) |
|