Handprinted character and word recognition

Sergey Tulyakov; Venu Govindaraju

doi:10.1007/978-0-85729-859-1_11

Handprinted character and word recognition

Sergey Tulyakov
, Venu Govindaraju

Research and Economic Development

SUNY Buffalo

Research output: Chapter in Book/Report/Conference proceeding › Chapter › peer-review

Abstract

The handprinted texts are produced when the writer tries to emulate some standard printed representation of the characters with the goal to make the written texts legible. Postal address blocks, different fillable forms, or other documents are among the examples of handprinting. Current chapter reviews the main techniques in recognizing handprinted characters and words. It outlines the characteristics of the handprinted texts, such as the stroke structure, distribution of strokes inside character bounding box, and frequently separated characters. Then it investigates how the reviewed techniques address such characteristics of the handprinted texts.

Original language	English
Title of host publication	Handbook of Document Image Processing and Recognition
Publisher	Springer London
Pages	359-389
Number of pages	31
ISBN (Electronic)	9780857298591
ISBN (Print)	9780857298584
DOIs	https://doi.org/10.1007/978-0-85729-859-1_11
State	Published - Jan 1 2014

Keywords

Binarization
Contour
Dynamic programming
Fillable forms
Handprinted word
Handprintedcharacter
Image histograms
K-nearest neighborrecognizer
Moments
Postal address
Segmentation
Skeleton
Zoning

Access to Document

10.1007/978-0-85729-859-1_11

Cite this

@inbook{c0cc050d88c04f7c9a7d82fd61fd566d,

title = "Handprinted character and word recognition",

abstract = "The handprinted texts are produced when the writer tries to emulate some standard printed representation of the characters with the goal to make the written texts legible. Postal address blocks, different fillable forms, or other documents are among the examples of handprinting. Current chapter reviews the main techniques in recognizing handprinted characters and words. It outlines the characteristics of the handprinted texts, such as the stroke structure, distribution of strokes inside character bounding box, and frequently separated characters. Then it investigates how the reviewed techniques address such characteristics of the handprinted texts.",

keywords = "Binarization, Contour, Dynamic programming, Fillable forms, Handprinted word, Handprintedcharacter, Image histograms, K-nearest neighborrecognizer, Moments, Postal address, Segmentation, Skeleton, Zoning",

author = "Sergey Tulyakov and Venu Govindaraju",

note = "Publisher Copyright: {\textcopyright} Springer-Verlag London 2014. All rights are reserved.",

year = "2014",

month = jan,

day = "1",

doi = "10.1007/978-0-85729-859-1\_11",

language = "English",

isbn = "9780857298584",

pages = "359--389",

booktitle = "Handbook of Document Image Processing and Recognition",

publisher = "Springer London",

address = "United Kingdom",

}

TY - CHAP

T1 - Handprinted character and word recognition

AU - Tulyakov, Sergey

AU - Govindaraju, Venu

N1 - Publisher Copyright: © Springer-Verlag London 2014. All rights are reserved.

PY - 2014/1/1

Y1 - 2014/1/1

N2 - The handprinted texts are produced when the writer tries to emulate some standard printed representation of the characters with the goal to make the written texts legible. Postal address blocks, different fillable forms, or other documents are among the examples of handprinting. Current chapter reviews the main techniques in recognizing handprinted characters and words. It outlines the characteristics of the handprinted texts, such as the stroke structure, distribution of strokes inside character bounding box, and frequently separated characters. Then it investigates how the reviewed techniques address such characteristics of the handprinted texts.

AB - The handprinted texts are produced when the writer tries to emulate some standard printed representation of the characters with the goal to make the written texts legible. Postal address blocks, different fillable forms, or other documents are among the examples of handprinting. Current chapter reviews the main techniques in recognizing handprinted characters and words. It outlines the characteristics of the handprinted texts, such as the stroke structure, distribution of strokes inside character bounding box, and frequently separated characters. Then it investigates how the reviewed techniques address such characteristics of the handprinted texts.

KW - Binarization

KW - Contour

KW - Dynamic programming

KW - Fillable forms

KW - Handprinted word

KW - Handprintedcharacter

KW - Image histograms

KW - K-nearest neighborrecognizer

KW - Moments

KW - Postal address

KW - Segmentation

KW - Skeleton

KW - Zoning

UR - https://www.scopus.com/pages/publications/85025709011

U2 - 10.1007/978-0-85729-859-1_11

DO - 10.1007/978-0-85729-859-1_11

M3 - Chapter

AN - SCOPUS:85025709011

SN - 9780857298584

SP - 359

EP - 389

BT - Handbook of Document Image Processing and Recognition

PB - Springer London

ER -

Handprinted character and word recognition

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this