Size and rotation invariant alphabet recognition

Junho Rim, Chul Hee Lee

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

As more vehicles and devices are becoming equipped with cameras, computer vision technologies can significantly enhance functionalities. Among various computer vision applications, alphabet recognition has been an important application. Alphabet recognition is a basic operation in text recognition of natural images, which can be used to obtain useful information from visual information. It can be used for vehicles or autonomous moving machines such as drones or robots to understand surrounding environments. A main difficulty is that alphabets can take various sizes and orientations. Thus, it is desirable to develop recognition algorithms that are size and rotation invariant. In this paper, we propose alphabet recognition algorithms based on the recently proposed angle-distance map, which is robust against size and rotation variations. Using the two features (distance and angle), the angle-distance map is generated, and a rotation invariant matching algorithm is developed. Since the distance is normalized, the map is size-invariant. Experimental results showed promising results.

Original languageEnglish
Title of host publicationUnmanned Systems Technology XIX
EditorsHoa G. Nguyen, Robert E. Karlsen, Charles M. Shoemaker, Douglas W. Gage
PublisherSPIE
ISBN (Electronic)9781510608917
DOIs
Publication statusPublished - 2017 Jan 1
EventUnmanned Systems Technology XIX Conference 2017 - Anaheim, United States
Duration: 2017 Apr 112017 Apr 13

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume10195
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Other

OtherUnmanned Systems Technology XIX Conference 2017
CountryUnited States
CityAnaheim
Period17/4/1117/4/13

Fingerprint

alphabets
Rotation Invariant
Computer vision
Recognition Algorithm
Angle
Computer Vision
computer vision
vehicles
Matching Algorithm
Cameras
Robots
robots
Robot
Camera
cameras
Invariant
Experimental Results

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Cite this

Rim, J., & Lee, C. H. (2017). Size and rotation invariant alphabet recognition. In H. G. Nguyen, R. E. Karlsen, C. M. Shoemaker, & D. W. Gage (Eds.), Unmanned Systems Technology XIX [1019517] (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 10195). SPIE. https://doi.org/10.1117/12.2263173
Rim, Junho ; Lee, Chul Hee. / Size and rotation invariant alphabet recognition. Unmanned Systems Technology XIX. editor / Hoa G. Nguyen ; Robert E. Karlsen ; Charles M. Shoemaker ; Douglas W. Gage. SPIE, 2017. (Proceedings of SPIE - The International Society for Optical Engineering).
@inproceedings{74718d318c38412e92b6f95f13cb5678,
title = "Size and rotation invariant alphabet recognition",
abstract = "As more vehicles and devices are becoming equipped with cameras, computer vision technologies can significantly enhance functionalities. Among various computer vision applications, alphabet recognition has been an important application. Alphabet recognition is a basic operation in text recognition of natural images, which can be used to obtain useful information from visual information. It can be used for vehicles or autonomous moving machines such as drones or robots to understand surrounding environments. A main difficulty is that alphabets can take various sizes and orientations. Thus, it is desirable to develop recognition algorithms that are size and rotation invariant. In this paper, we propose alphabet recognition algorithms based on the recently proposed angle-distance map, which is robust against size and rotation variations. Using the two features (distance and angle), the angle-distance map is generated, and a rotation invariant matching algorithm is developed. Since the distance is normalized, the map is size-invariant. Experimental results showed promising results.",
author = "Junho Rim and Lee, {Chul Hee}",
year = "2017",
month = "1",
day = "1",
doi = "10.1117/12.2263173",
language = "English",
series = "Proceedings of SPIE - The International Society for Optical Engineering",
publisher = "SPIE",
editor = "Nguyen, {Hoa G.} and Karlsen, {Robert E.} and Shoemaker, {Charles M.} and Gage, {Douglas W.}",
booktitle = "Unmanned Systems Technology XIX",
address = "United States",

}

Rim, J & Lee, CH 2017, Size and rotation invariant alphabet recognition. in HG Nguyen, RE Karlsen, CM Shoemaker & DW Gage (eds), Unmanned Systems Technology XIX., 1019517, Proceedings of SPIE - The International Society for Optical Engineering, vol. 10195, SPIE, Unmanned Systems Technology XIX Conference 2017, Anaheim, United States, 17/4/11. https://doi.org/10.1117/12.2263173

Size and rotation invariant alphabet recognition. / Rim, Junho; Lee, Chul Hee.

Unmanned Systems Technology XIX. ed. / Hoa G. Nguyen; Robert E. Karlsen; Charles M. Shoemaker; Douglas W. Gage. SPIE, 2017. 1019517 (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 10195).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Size and rotation invariant alphabet recognition

AU - Rim, Junho

AU - Lee, Chul Hee

PY - 2017/1/1

Y1 - 2017/1/1

N2 - As more vehicles and devices are becoming equipped with cameras, computer vision technologies can significantly enhance functionalities. Among various computer vision applications, alphabet recognition has been an important application. Alphabet recognition is a basic operation in text recognition of natural images, which can be used to obtain useful information from visual information. It can be used for vehicles or autonomous moving machines such as drones or robots to understand surrounding environments. A main difficulty is that alphabets can take various sizes and orientations. Thus, it is desirable to develop recognition algorithms that are size and rotation invariant. In this paper, we propose alphabet recognition algorithms based on the recently proposed angle-distance map, which is robust against size and rotation variations. Using the two features (distance and angle), the angle-distance map is generated, and a rotation invariant matching algorithm is developed. Since the distance is normalized, the map is size-invariant. Experimental results showed promising results.

AB - As more vehicles and devices are becoming equipped with cameras, computer vision technologies can significantly enhance functionalities. Among various computer vision applications, alphabet recognition has been an important application. Alphabet recognition is a basic operation in text recognition of natural images, which can be used to obtain useful information from visual information. It can be used for vehicles or autonomous moving machines such as drones or robots to understand surrounding environments. A main difficulty is that alphabets can take various sizes and orientations. Thus, it is desirable to develop recognition algorithms that are size and rotation invariant. In this paper, we propose alphabet recognition algorithms based on the recently proposed angle-distance map, which is robust against size and rotation variations. Using the two features (distance and angle), the angle-distance map is generated, and a rotation invariant matching algorithm is developed. Since the distance is normalized, the map is size-invariant. Experimental results showed promising results.

UR - http://www.scopus.com/inward/record.url?scp=85039425069&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85039425069&partnerID=8YFLogxK

U2 - 10.1117/12.2263173

DO - 10.1117/12.2263173

M3 - Conference contribution

AN - SCOPUS:85039425069

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - Unmanned Systems Technology XIX

A2 - Nguyen, Hoa G.

A2 - Karlsen, Robert E.

A2 - Shoemaker, Charles M.

A2 - Gage, Douglas W.

PB - SPIE

ER -

Rim J, Lee CH. Size and rotation invariant alphabet recognition. In Nguyen HG, Karlsen RE, Shoemaker CM, Gage DW, editors, Unmanned Systems Technology XIX. SPIE. 2017. 1019517. (Proceedings of SPIE - The International Society for Optical Engineering). https://doi.org/10.1117/12.2263173