Reliable image matching using binarized gradient features obtained with multi-flash camera

Yasunori Sakuramoto, Yuichi Kanematsu, Shuichi Akizuki, Manabu Hashimoto, Kiyotaka Watanabe, Makito Seki

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

Abstract

In this paper, we propose an object detection method using features describing information about a concavoconvex shape of an object that are obtained by using a small camera that controls the illumination direction. A feature image containing information about the shape of the object is generated by integrating images obtained by turning on, one by one, light emitting diodes (LEDs) annularly arranged around the camera. Our method can reliably detect a texture-less object by using this feature image in the matching process. Experiments using 200 actual images confirmed that the method achieves a 97.5% recognition success rate and a 4.62 sec processing time.

Original languageEnglish
Title of host publicationVISAPP 2015 - 10th International Conference on Computer Vision Theory and Applications; VISIGRAPP, Proceedings
PublisherSciTePress
Pages260-264
Number of pages5
Volume2
ISBN (Electronic)9789897580901
Publication statusPublished - 2015
Externally publishedYes
Event10th International Conference on Computer Vision Theory and Applications, VISAPP 2015 - Berlin, Germany
Duration: 2015 Mar 112015 Mar 14

Other

Other10th International Conference on Computer Vision Theory and Applications, VISAPP 2015
CountryGermany
CityBerlin
Period15/3/1115/3/14

Fingerprint

Image matching
Cameras
Light emitting diodes
Textures
Lighting
Processing
Experiments
Object detection

Keywords

  • Binarized gradient features
  • Binary code
  • Image matching
  • Object detection
  • Texture-less

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition

Cite this

Sakuramoto, Y., Kanematsu, Y., Akizuki, S., Hashimoto, M., Watanabe, K., & Seki, M. (2015). Reliable image matching using binarized gradient features obtained with multi-flash camera. In VISAPP 2015 - 10th International Conference on Computer Vision Theory and Applications; VISIGRAPP, Proceedings (Vol. 2, pp. 260-264). SciTePress.

Reliable image matching using binarized gradient features obtained with multi-flash camera. / Sakuramoto, Yasunori; Kanematsu, Yuichi; Akizuki, Shuichi; Hashimoto, Manabu; Watanabe, Kiyotaka; Seki, Makito.

VISAPP 2015 - 10th International Conference on Computer Vision Theory and Applications; VISIGRAPP, Proceedings. Vol. 2 SciTePress, 2015. p. 260-264.

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

Sakuramoto, Y, Kanematsu, Y, Akizuki, S, Hashimoto, M, Watanabe, K & Seki, M 2015, Reliable image matching using binarized gradient features obtained with multi-flash camera. in VISAPP 2015 - 10th International Conference on Computer Vision Theory and Applications; VISIGRAPP, Proceedings. vol. 2, SciTePress, pp. 260-264, 10th International Conference on Computer Vision Theory and Applications, VISAPP 2015, Berlin, Germany, 15/3/11.
Sakuramoto Y, Kanematsu Y, Akizuki S, Hashimoto M, Watanabe K, Seki M. Reliable image matching using binarized gradient features obtained with multi-flash camera. In VISAPP 2015 - 10th International Conference on Computer Vision Theory and Applications; VISIGRAPP, Proceedings. Vol. 2. SciTePress. 2015. p. 260-264
Sakuramoto, Yasunori ; Kanematsu, Yuichi ; Akizuki, Shuichi ; Hashimoto, Manabu ; Watanabe, Kiyotaka ; Seki, Makito. / Reliable image matching using binarized gradient features obtained with multi-flash camera. VISAPP 2015 - 10th International Conference on Computer Vision Theory and Applications; VISIGRAPP, Proceedings. Vol. 2 SciTePress, 2015. pp. 260-264
@inproceedings{910a0a3c5c8248d9b15a045a0da6fab1,
title = "Reliable image matching using binarized gradient features obtained with multi-flash camera",
abstract = "In this paper, we propose an object detection method using features describing information about a concavoconvex shape of an object that are obtained by using a small camera that controls the illumination direction. A feature image containing information about the shape of the object is generated by integrating images obtained by turning on, one by one, light emitting diodes (LEDs) annularly arranged around the camera. Our method can reliably detect a texture-less object by using this feature image in the matching process. Experiments using 200 actual images confirmed that the method achieves a 97.5{\%} recognition success rate and a 4.62 sec processing time.",
keywords = "Binarized gradient features, Binary code, Image matching, Object detection, Texture-less",
author = "Yasunori Sakuramoto and Yuichi Kanematsu and Shuichi Akizuki and Manabu Hashimoto and Kiyotaka Watanabe and Makito Seki",
year = "2015",
language = "English",
volume = "2",
pages = "260--264",
booktitle = "VISAPP 2015 - 10th International Conference on Computer Vision Theory and Applications; VISIGRAPP, Proceedings",
publisher = "SciTePress",

}

TY - GEN

T1 - Reliable image matching using binarized gradient features obtained with multi-flash camera

AU - Sakuramoto, Yasunori

AU - Kanematsu, Yuichi

AU - Akizuki, Shuichi

AU - Hashimoto, Manabu

AU - Watanabe, Kiyotaka

AU - Seki, Makito

PY - 2015

Y1 - 2015

N2 - In this paper, we propose an object detection method using features describing information about a concavoconvex shape of an object that are obtained by using a small camera that controls the illumination direction. A feature image containing information about the shape of the object is generated by integrating images obtained by turning on, one by one, light emitting diodes (LEDs) annularly arranged around the camera. Our method can reliably detect a texture-less object by using this feature image in the matching process. Experiments using 200 actual images confirmed that the method achieves a 97.5% recognition success rate and a 4.62 sec processing time.

AB - In this paper, we propose an object detection method using features describing information about a concavoconvex shape of an object that are obtained by using a small camera that controls the illumination direction. A feature image containing information about the shape of the object is generated by integrating images obtained by turning on, one by one, light emitting diodes (LEDs) annularly arranged around the camera. Our method can reliably detect a texture-less object by using this feature image in the matching process. Experiments using 200 actual images confirmed that the method achieves a 97.5% recognition success rate and a 4.62 sec processing time.

KW - Binarized gradient features

KW - Binary code

KW - Image matching

KW - Object detection

KW - Texture-less

UR - http://www.scopus.com/inward/record.url?scp=84939482470&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84939482470&partnerID=8YFLogxK

M3 - Conference contribution

VL - 2

SP - 260

EP - 264

BT - VISAPP 2015 - 10th International Conference on Computer Vision Theory and Applications; VISIGRAPP, Proceedings

PB - SciTePress

ER -