1998
DOI: 10.1016/s0262-8856(98)00055-9
|View full text |Cite
|
Sign up to set email alerts
|

Text identification for document image analysis using a neural network

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
22
0

Year Published

1999
1999
2023
2023

Publication Types

Select...
4
3
1

Relationship

0
8

Authors

Journals

citations
Cited by 53 publications
(22 citation statements)
references
References 18 publications
0
22
0
Order By: Relevance
“…Feature used in the proposed system is the document structure element DSE [19]. It is based on a 3x3 blocks.…”
Section: Textural Based Featuresmentioning
confidence: 99%
“…Feature used in the proposed system is the document structure element DSE [19]. It is based on a 3x3 blocks.…”
Section: Textural Based Featuresmentioning
confidence: 99%
“…Neural network-based classification is a well-explored area, e.g. [6,16,41]. The first method uses a neural network to classify a set of masks into the three texture classes in the page segmentation problem: halftone, background, and text and line-drawing regions.…”
Section: Segment Recognitionmentioning
confidence: 99%
“…The text and line-drawing regions are further discriminated based on connectivity analysis. Recognition of textual and graphic blocks has been done using self organizing maps [41]. Radial basis function and probabilistic neural networks are applied to region classification, [16].…”
Section: Segment Recognitionmentioning
confidence: 99%
“…• neural networks to OCR/ICR and text identification algorithms [4], [12]; • Hough transform to object identification [9]. Our method of evaluation sketched function graphs relies on…”
Section: Introductionmentioning
confidence: 99%