Food region detection using Bag-of-Features representation and color feature

Ruiko Miyano, Yuko Uematsu, Hideo Saito

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

2 Citations (Scopus)

Abstract

Food image processing has recently attracted attention, because many people take photos of food. For food image processing, recognition of captured food is an essential technology, but region detection of the food area from captured photos is also very important procedure for food recognition. In this paper, we propose a novel method for automatic region detection of food from photos using two kinds of features in input image. To detect food regions, we use a method which is widely used in generic object recognition. We divide an image into small subregions and represent each subregion as Bag-of-Features representation using local feature descriptors and color feature. Using two features, we recognize food subregions and finally connect them as food regions. Our experiments show that the proposed method can detect food region in high accuracy.

Original languageEnglish
Title of host publicationVISAPP 2012 - Proceedings of the International Conference on Computer Vision Theory and Applications
Pages709-713
Number of pages5
Volume1
Publication statusPublished - 2012
EventInternational Conference on Computer Vision Theory and Applications, VISAPP 2012 - Rome, Italy
Duration: 2012 Feb 242012 Feb 26

Other

OtherInternational Conference on Computer Vision Theory and Applications, VISAPP 2012
CountryItaly
CityRome
Period12/2/2412/2/26

Fingerprint

Color
Image processing
Object recognition
Experiments

Keywords

  • Bag-of-Features
  • Color feature
  • Food region detection
  • Support vector machine
  • SURF
  • Visual words

ASJC Scopus subject areas

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

Cite this

Miyano, R., Uematsu, Y., & Saito, H. (2012). Food region detection using Bag-of-Features representation and color feature. In VISAPP 2012 - Proceedings of the International Conference on Computer Vision Theory and Applications (Vol. 1, pp. 709-713)

Food region detection using Bag-of-Features representation and color feature. / Miyano, Ruiko; Uematsu, Yuko; Saito, Hideo.

VISAPP 2012 - Proceedings of the International Conference on Computer Vision Theory and Applications. Vol. 1 2012. p. 709-713.

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

Miyano, R, Uematsu, Y & Saito, H 2012, Food region detection using Bag-of-Features representation and color feature. in VISAPP 2012 - Proceedings of the International Conference on Computer Vision Theory and Applications. vol. 1, pp. 709-713, International Conference on Computer Vision Theory and Applications, VISAPP 2012, Rome, Italy, 12/2/24.
Miyano R, Uematsu Y, Saito H. Food region detection using Bag-of-Features representation and color feature. In VISAPP 2012 - Proceedings of the International Conference on Computer Vision Theory and Applications. Vol. 1. 2012. p. 709-713
Miyano, Ruiko ; Uematsu, Yuko ; Saito, Hideo. / Food region detection using Bag-of-Features representation and color feature. VISAPP 2012 - Proceedings of the International Conference on Computer Vision Theory and Applications. Vol. 1 2012. pp. 709-713
@inproceedings{f68673f812104b61af07e919aa5a5135,
title = "Food region detection using Bag-of-Features representation and color feature",
abstract = "Food image processing has recently attracted attention, because many people take photos of food. For food image processing, recognition of captured food is an essential technology, but region detection of the food area from captured photos is also very important procedure for food recognition. In this paper, we propose a novel method for automatic region detection of food from photos using two kinds of features in input image. To detect food regions, we use a method which is widely used in generic object recognition. We divide an image into small subregions and represent each subregion as Bag-of-Features representation using local feature descriptors and color feature. Using two features, we recognize food subregions and finally connect them as food regions. Our experiments show that the proposed method can detect food region in high accuracy.",
keywords = "Bag-of-Features, Color feature, Food region detection, Support vector machine, SURF, Visual words",
author = "Ruiko Miyano and Yuko Uematsu and Hideo Saito",
year = "2012",
language = "English",
isbn = "9789898565037",
volume = "1",
pages = "709--713",
booktitle = "VISAPP 2012 - Proceedings of the International Conference on Computer Vision Theory and Applications",

}

TY - GEN

T1 - Food region detection using Bag-of-Features representation and color feature

AU - Miyano, Ruiko

AU - Uematsu, Yuko

AU - Saito, Hideo

PY - 2012

Y1 - 2012

N2 - Food image processing has recently attracted attention, because many people take photos of food. For food image processing, recognition of captured food is an essential technology, but region detection of the food area from captured photos is also very important procedure for food recognition. In this paper, we propose a novel method for automatic region detection of food from photos using two kinds of features in input image. To detect food regions, we use a method which is widely used in generic object recognition. We divide an image into small subregions and represent each subregion as Bag-of-Features representation using local feature descriptors and color feature. Using two features, we recognize food subregions and finally connect them as food regions. Our experiments show that the proposed method can detect food region in high accuracy.

AB - Food image processing has recently attracted attention, because many people take photos of food. For food image processing, recognition of captured food is an essential technology, but region detection of the food area from captured photos is also very important procedure for food recognition. In this paper, we propose a novel method for automatic region detection of food from photos using two kinds of features in input image. To detect food regions, we use a method which is widely used in generic object recognition. We divide an image into small subregions and represent each subregion as Bag-of-Features representation using local feature descriptors and color feature. Using two features, we recognize food subregions and finally connect them as food regions. Our experiments show that the proposed method can detect food region in high accuracy.

KW - Bag-of-Features

KW - Color feature

KW - Food region detection

KW - Support vector machine

KW - SURF

KW - Visual words

UR - http://www.scopus.com/inward/record.url?scp=84862123646&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84862123646&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84862123646

SN - 9789898565037

VL - 1

SP - 709

EP - 713

BT - VISAPP 2012 - Proceedings of the International Conference on Computer Vision Theory and Applications

ER -