Object Class Recognition Using Surf Descriptors and Shape Skeletons

Vahid Alizadeh Sahzabi, Khairuddin Omar

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

Abstract

This paper presents a method to classify new objects with SURF descriptors and shape skeleton of objects in dataset. The objective of the research is to classify all objects which exist in all images. Stages in this method are consisting of three main stages: image segmentation, object recognition and object class recognition. The region of interest in this method is used the saliency based region selection. In this paper, SIFT and SURF also compare in aspects of speed and recognition accuracy too. The result has shown SURF cluttered dataset has a better accuracy and it is faster. Also for object class recognition purpose shape skeleton would help to classify same category objects. Finally the outputs will be train with fuzzy logic to make an accurate decision making. Results have shown the accuracy improved up to 94%.

Original languageEnglish
Title of host publicationCommunications in Computer and Information Science
PublisherSpringer Verlag
Pages255-264
Number of pages10
Volume376 CCIS
ISBN (Print)9783642404085
DOIs
Publication statusPublished - 2013
Event16th FIRA RoboWorld Congress, FIRA 2013 - Kuala Lumpur
Duration: 24 Aug 201329 Aug 2013

Publication series

NameCommunications in Computer and Information Science
Volume376 CCIS
ISSN (Print)18650929

Other

Other16th FIRA RoboWorld Congress, FIRA 2013
CityKuala Lumpur
Period24/8/1329/8/13

Fingerprint

Object recognition
Image segmentation
Fuzzy logic
Decision making

Keywords

  • Fuzzy logic
  • Object class recognition
  • Object classification
  • Object recognition
  • Shape matching
  • Skeleton
  • SURF

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Sahzabi, V. A., & Omar, K. (2013). Object Class Recognition Using Surf Descriptors and Shape Skeletons. In Communications in Computer and Information Science (Vol. 376 CCIS, pp. 255-264). (Communications in Computer and Information Science; Vol. 376 CCIS). Springer Verlag. https://doi.org/10.1007/978-3-642-40409-2_22

Object Class Recognition Using Surf Descriptors and Shape Skeletons. / Sahzabi, Vahid Alizadeh; Omar, Khairuddin.

Communications in Computer and Information Science. Vol. 376 CCIS Springer Verlag, 2013. p. 255-264 (Communications in Computer and Information Science; Vol. 376 CCIS).

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

Sahzabi, VA & Omar, K 2013, Object Class Recognition Using Surf Descriptors and Shape Skeletons. in Communications in Computer and Information Science. vol. 376 CCIS, Communications in Computer and Information Science, vol. 376 CCIS, Springer Verlag, pp. 255-264, 16th FIRA RoboWorld Congress, FIRA 2013, Kuala Lumpur, 24/8/13. https://doi.org/10.1007/978-3-642-40409-2_22
Sahzabi VA, Omar K. Object Class Recognition Using Surf Descriptors and Shape Skeletons. In Communications in Computer and Information Science. Vol. 376 CCIS. Springer Verlag. 2013. p. 255-264. (Communications in Computer and Information Science). https://doi.org/10.1007/978-3-642-40409-2_22
Sahzabi, Vahid Alizadeh ; Omar, Khairuddin. / Object Class Recognition Using Surf Descriptors and Shape Skeletons. Communications in Computer and Information Science. Vol. 376 CCIS Springer Verlag, 2013. pp. 255-264 (Communications in Computer and Information Science).
@inproceedings{f2bb646cf3c14110becf34871c26e352,
title = "Object Class Recognition Using Surf Descriptors and Shape Skeletons",
abstract = "This paper presents a method to classify new objects with SURF descriptors and shape skeleton of objects in dataset. The objective of the research is to classify all objects which exist in all images. Stages in this method are consisting of three main stages: image segmentation, object recognition and object class recognition. The region of interest in this method is used the saliency based region selection. In this paper, SIFT and SURF also compare in aspects of speed and recognition accuracy too. The result has shown SURF cluttered dataset has a better accuracy and it is faster. Also for object class recognition purpose shape skeleton would help to classify same category objects. Finally the outputs will be train with fuzzy logic to make an accurate decision making. Results have shown the accuracy improved up to 94{\%}.",
keywords = "Fuzzy logic, Object class recognition, Object classification, Object recognition, Shape matching, Skeleton, SURF",
author = "Sahzabi, {Vahid Alizadeh} and Khairuddin Omar",
year = "2013",
doi = "10.1007/978-3-642-40409-2_22",
language = "English",
isbn = "9783642404085",
volume = "376 CCIS",
series = "Communications in Computer and Information Science",
publisher = "Springer Verlag",
pages = "255--264",
booktitle = "Communications in Computer and Information Science",

}

TY - GEN

T1 - Object Class Recognition Using Surf Descriptors and Shape Skeletons

AU - Sahzabi, Vahid Alizadeh

AU - Omar, Khairuddin

PY - 2013

Y1 - 2013

N2 - This paper presents a method to classify new objects with SURF descriptors and shape skeleton of objects in dataset. The objective of the research is to classify all objects which exist in all images. Stages in this method are consisting of three main stages: image segmentation, object recognition and object class recognition. The region of interest in this method is used the saliency based region selection. In this paper, SIFT and SURF also compare in aspects of speed and recognition accuracy too. The result has shown SURF cluttered dataset has a better accuracy and it is faster. Also for object class recognition purpose shape skeleton would help to classify same category objects. Finally the outputs will be train with fuzzy logic to make an accurate decision making. Results have shown the accuracy improved up to 94%.

AB - This paper presents a method to classify new objects with SURF descriptors and shape skeleton of objects in dataset. The objective of the research is to classify all objects which exist in all images. Stages in this method are consisting of three main stages: image segmentation, object recognition and object class recognition. The region of interest in this method is used the saliency based region selection. In this paper, SIFT and SURF also compare in aspects of speed and recognition accuracy too. The result has shown SURF cluttered dataset has a better accuracy and it is faster. Also for object class recognition purpose shape skeleton would help to classify same category objects. Finally the outputs will be train with fuzzy logic to make an accurate decision making. Results have shown the accuracy improved up to 94%.

KW - Fuzzy logic

KW - Object class recognition

KW - Object classification

KW - Object recognition

KW - Shape matching

KW - Skeleton

KW - SURF

UR - http://www.scopus.com/inward/record.url?scp=84904630905&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84904630905&partnerID=8YFLogxK

U2 - 10.1007/978-3-642-40409-2_22

DO - 10.1007/978-3-642-40409-2_22

M3 - Conference contribution

SN - 9783642404085

VL - 376 CCIS

T3 - Communications in Computer and Information Science

SP - 255

EP - 264

BT - Communications in Computer and Information Science

PB - Springer Verlag

ER -