Visual object categorization based on orientation descriptor

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

2 Citations (Scopus)

Abstract

The demand of new fast technology and image investigation in many applications has made managing visual object categorization techniques extremely important. The main problem of visual object categorization is the semantic gap (categorization problem). Currently, several researches show that using a texture feature could improve the categorization problem especially when using orientation descriptors. Mainly, in this research the edge histogram descriptor has been selected to extract the texture feature. Obviously, the main demerit of using this kind of texture descriptor is it uses single orientation to extract the texture feature. Therefore, the Gabor filter has been proposed to improve the performance of this descriptor by constructing different feature maps based on different scale and orientation. To demonstrate the performance of the proposed method, the first 20 classes of the Caltech 101 dataset have been used. Moreover, we compared the performance recognition of the proposed method in two different domains, namely spatial and frequency domains. Finally, the result shows that the proposed method in the spatial domain outperforms the proposed method in the frequency domain. This is because of losing some of the basic raw data though using Fast Fourier Transform algorithm in converting the system to the frequency domain.

Original languageEnglish
Title of host publicationProceedings - 6th Asia International Conference on Mathematical Modelling and Computer Simulation, AMS 2012
Pages70-74
Number of pages5
DOIs
Publication statusPublished - 2012
Event6th Asia International Conference on Mathematical Modelling and Computer Simulation, AMS 2012 - Bali
Duration: 29 May 201231 May 2012

Other

Other6th Asia International Conference on Mathematical Modelling and Computer Simulation, AMS 2012
CityBali
Period29/5/1231/5/12

Fingerprint

Categorization
Descriptors
Texture Feature
Textures
Frequency Domain
Gabor filters
Gabor Filter
Fast Fourier transform
Fast Fourier transforms
Histogram
Texture
Semantics
Vision
Object
Demonstrate

Keywords

  • Edge histogram descripto
  • Gabor filte
  • naïve appraoch
  • VOC technique

ASJC Scopus subject areas

  • Modelling and Simulation

Cite this

Ayad, H., Sheikh Abdullah, S. N. H., & Abdullah, A. (2012). Visual object categorization based on orientation descriptor. In Proceedings - 6th Asia International Conference on Mathematical Modelling and Computer Simulation, AMS 2012 (pp. 70-74). [6243924] https://doi.org/10.1109/AMS.2012.43

Visual object categorization based on orientation descriptor. / Ayad, Hayder; Sheikh Abdullah, Siti Norul Huda; Abdullah, Azizi.

Proceedings - 6th Asia International Conference on Mathematical Modelling and Computer Simulation, AMS 2012. 2012. p. 70-74 6243924.

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

Ayad, H, Sheikh Abdullah, SNH & Abdullah, A 2012, Visual object categorization based on orientation descriptor. in Proceedings - 6th Asia International Conference on Mathematical Modelling and Computer Simulation, AMS 2012., 6243924, pp. 70-74, 6th Asia International Conference on Mathematical Modelling and Computer Simulation, AMS 2012, Bali, 29/5/12. https://doi.org/10.1109/AMS.2012.43
Ayad H, Sheikh Abdullah SNH, Abdullah A. Visual object categorization based on orientation descriptor. In Proceedings - 6th Asia International Conference on Mathematical Modelling and Computer Simulation, AMS 2012. 2012. p. 70-74. 6243924 https://doi.org/10.1109/AMS.2012.43
Ayad, Hayder ; Sheikh Abdullah, Siti Norul Huda ; Abdullah, Azizi. / Visual object categorization based on orientation descriptor. Proceedings - 6th Asia International Conference on Mathematical Modelling and Computer Simulation, AMS 2012. 2012. pp. 70-74
@inproceedings{0d1c3686d90e424bab590d9fc9039039,
title = "Visual object categorization based on orientation descriptor",
abstract = "The demand of new fast technology and image investigation in many applications has made managing visual object categorization techniques extremely important. The main problem of visual object categorization is the semantic gap (categorization problem). Currently, several researches show that using a texture feature could improve the categorization problem especially when using orientation descriptors. Mainly, in this research the edge histogram descriptor has been selected to extract the texture feature. Obviously, the main demerit of using this kind of texture descriptor is it uses single orientation to extract the texture feature. Therefore, the Gabor filter has been proposed to improve the performance of this descriptor by constructing different feature maps based on different scale and orientation. To demonstrate the performance of the proposed method, the first 20 classes of the Caltech 101 dataset have been used. Moreover, we compared the performance recognition of the proposed method in two different domains, namely spatial and frequency domains. Finally, the result shows that the proposed method in the spatial domain outperforms the proposed method in the frequency domain. This is because of losing some of the basic raw data though using Fast Fourier Transform algorithm in converting the system to the frequency domain.",
keywords = "Edge histogram descripto, Gabor filte, na{\"i}ve appraoch, VOC technique",
author = "Hayder Ayad and {Sheikh Abdullah}, {Siti Norul Huda} and Azizi Abdullah",
year = "2012",
doi = "10.1109/AMS.2012.43",
language = "English",
isbn = "9780769547305",
pages = "70--74",
booktitle = "Proceedings - 6th Asia International Conference on Mathematical Modelling and Computer Simulation, AMS 2012",

}

TY - GEN

T1 - Visual object categorization based on orientation descriptor

AU - Ayad, Hayder

AU - Sheikh Abdullah, Siti Norul Huda

AU - Abdullah, Azizi

PY - 2012

Y1 - 2012

N2 - The demand of new fast technology and image investigation in many applications has made managing visual object categorization techniques extremely important. The main problem of visual object categorization is the semantic gap (categorization problem). Currently, several researches show that using a texture feature could improve the categorization problem especially when using orientation descriptors. Mainly, in this research the edge histogram descriptor has been selected to extract the texture feature. Obviously, the main demerit of using this kind of texture descriptor is it uses single orientation to extract the texture feature. Therefore, the Gabor filter has been proposed to improve the performance of this descriptor by constructing different feature maps based on different scale and orientation. To demonstrate the performance of the proposed method, the first 20 classes of the Caltech 101 dataset have been used. Moreover, we compared the performance recognition of the proposed method in two different domains, namely spatial and frequency domains. Finally, the result shows that the proposed method in the spatial domain outperforms the proposed method in the frequency domain. This is because of losing some of the basic raw data though using Fast Fourier Transform algorithm in converting the system to the frequency domain.

AB - The demand of new fast technology and image investigation in many applications has made managing visual object categorization techniques extremely important. The main problem of visual object categorization is the semantic gap (categorization problem). Currently, several researches show that using a texture feature could improve the categorization problem especially when using orientation descriptors. Mainly, in this research the edge histogram descriptor has been selected to extract the texture feature. Obviously, the main demerit of using this kind of texture descriptor is it uses single orientation to extract the texture feature. Therefore, the Gabor filter has been proposed to improve the performance of this descriptor by constructing different feature maps based on different scale and orientation. To demonstrate the performance of the proposed method, the first 20 classes of the Caltech 101 dataset have been used. Moreover, we compared the performance recognition of the proposed method in two different domains, namely spatial and frequency domains. Finally, the result shows that the proposed method in the spatial domain outperforms the proposed method in the frequency domain. This is because of losing some of the basic raw data though using Fast Fourier Transform algorithm in converting the system to the frequency domain.

KW - Edge histogram descripto

KW - Gabor filte

KW - naïve appraoch

KW - VOC technique

UR - http://www.scopus.com/inward/record.url?scp=84866552308&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84866552308&partnerID=8YFLogxK

U2 - 10.1109/AMS.2012.43

DO - 10.1109/AMS.2012.43

M3 - Conference contribution

AN - SCOPUS:84866552308

SN - 9780769547305

SP - 70

EP - 74

BT - Proceedings - 6th Asia International Conference on Mathematical Modelling and Computer Simulation, AMS 2012

ER -