2008
DOI: 10.1016/j.patcog.2007.10.017
|View full text |Cite
|
Sign up to set email alerts
|

Retrieval of machine-printed Latin documents through Word Shape Coding

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
22
0

Year Published

2008
2008
2019
2019

Publication Types

Select...
3
3
2

Relationship

0
8

Authors

Journals

citations
Cited by 28 publications
(22 citation statements)
references
References 20 publications
0
22
0
Order By: Relevance
“…Now, from each disconnected component of the upper and lower part, the locations of extreme points are considered as feature values (F 3 ). Six coding values (1)(2)(3)(4)(5)(6) are employed according to the position of extreme points.…”
Section: Coding Based On Extreme Pointsmentioning
confidence: 99%
See 1 more Smart Citation
“…Now, from each disconnected component of the upper and lower part, the locations of extreme points are considered as feature values (F 3 ). Six coding values (1)(2)(3)(4)(5)(6) are employed according to the position of extreme points.…”
Section: Coding Based On Extreme Pointsmentioning
confidence: 99%
“…The training free approach can be categorized into two main categories, such as i) Segmentation based word spotting ii) Segmentation free word spotting. A notable work of segmentation based word spotting system, based on shape coding scheme, can be found in [5,4]. To overcome the problem of segmentation, segmentation free word spotting techniques are proposed in literature [7].…”
Section: Introductionmentioning
confidence: 99%
“…Recently, Lu and Tan propose in [12] a very simple typewritten word coding which is useful enough to characterize documents. The proposed word code is based on character extremum points and horizontal cuts.…”
Section: Word Spottingmentioning
confidence: 99%
“…Each topic uses its own techniques to achieve the localization. Word spotting benefits from the fact that text strings are one-dimensional structures and can apply one-dimensional compact codes as Lu and Tan do in [12] to easily retrieve similar words to the queried one. On the other hand, symbol spotting benefits from the fact that symbols are synthetical entities consisting of uniform regions which are usually highly structured.…”
Section: Introductionmentioning
confidence: 99%
“…The detection of the keyword in a document image is done by a cross-correlation approach between the prototype signature and signatures extracted from the target document image. A number of contributions exist in the literature on word spotting methods both for typewritten documents [8,12], and handwritten documents [15,18]. In the sketch-based annotation framework described in this paper, we perform a word spotting approach as the action associated to a sequence of user gestures.…”
Section: Word Spotting For Knowledge Extractionmentioning
confidence: 99%