AUTOMATIC 3D OBJECT RECOGNITION BASED ON SIMULTANEOUS UTILIZATION OF ARTIFICIAL INTELLIGENCE AND INFORMATION FUSION CONCEPTS

Q: How can I download an article?

To download an article from SID, first log in to the site, search for the article title, and click on the 'Download Article' option.

Q: How can I download an ISI article?

To download an ISI article on SID, enter the keyword or article title in the search bar, view the relevant results, click on the desired article, and select the 'Download Article' option.

Q: How can I access the SID database?

To access the SID database, visit SID.ir, create an account, and log in to access scientific resources.

Q: Is downloading articles from SID free?

Some articles on SID are available for free, while others require payment. Details are specified on the article's page.

SAMDZADEGAN F.; LUCAS C.; AZIZI A.

مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resources

Journal Paper

Paper Information

Journal: Year:2002 | Volume:36 | Issue:1 (75) Page(s): 47-62

Download Full-Text

Persian Verion

View:

1,053

Download:

Cites:

Information Journal Paper

Title

AUTOMATIC 3D OBJECT RECOGNITION BASED ON SIMULTANEOUS UTILIZATION OF ARTIFICIAL INTELLIGENCE AND INFORMATION FUSION CONCEPTS

Author(s)

SAMDZADEGAN F. | LUCAS C. | AZIZI A. | Issue Writer Certificate

Keywords

Not Registered.

Abstract

In this paper a novel non-parametric approach for the 3D object recognition from digital/digitized images is presented. Due to the non-deterministic behavior and complexities associated with the object recognition process, the proposed method incorporates a fuzzy reasoning strategy for the object recognition process. The proposed recognition method takes advantage of all descriptive parameters that define a 3D object in an integral manner. These are objects structural, textural and spectral attributes. The structural attributes are related to the 3D construction (such as shape, size and relief) of the object and are extracted from the generated underlying DSM. The textural information is extracted from the corresponding 2D regions in image space. 2D regions are determined using a fuzzy based region growing strategy. The spectral information is extracted using a mean value calculated for the radiometric information included in 2D regions using all available multi spectral spaces. These descriptive attributes are fused simultaneously using Mamdani and Takagi-Sugeno fuzzy inference strategy. The proposed recognition method is also embedded with training potentials. The training potentials are realized by incorporating a neuro fuzzy technique by which the originally defined membership functions can be modified. This means that the parameter definitions are automatically tuned when unrecognized objects encountered. This paper describes the implemented recognition and training strategy. This is followed by a report of the test results conducted for the evaluation of the proposed method. The tests demonstrate promising results.

Cites

No record.

References

No record.

Cite

APA: Copy

SAMDZADEGAN, F., LUCAS, C., & AZIZI, A.. (2002). AUTOMATIC 3D OBJECT RECOGNITION BASED ON SIMULTANEOUS UTILIZATION OF ARTIFICIAL INTELLIGENCE AND INFORMATION FUSION CONCEPTS. JOURNAL OF FACULTY OF ENGINEERING (UNIVERSITY OF TEHRAN), 36(1 (75)), 47-62. SID. https://sid.ir/paper/357336/en

Vancouver: Copy

SAMDZADEGAN F., LUCAS C., AZIZI A.. AUTOMATIC 3D OBJECT RECOGNITION BASED ON SIMULTANEOUS UTILIZATION OF ARTIFICIAL INTELLIGENCE AND INFORMATION FUSION CONCEPTS. JOURNAL OF FACULTY OF ENGINEERING (UNIVERSITY OF TEHRAN)[Internet]. 2002;36(1 (75)):47-62. Available from: https://sid.ir/paper/357336/en

IEEE: Copy

F. SAMDZADEGAN, C. LUCAS, and A. AZIZI, “AUTOMATIC 3D OBJECT RECOGNITION BASED ON SIMULTANEOUS UTILIZATION OF ARTIFICIAL INTELLIGENCE AND INFORMATION FUSION CONCEPTS,” JOURNAL OF FACULTY OF ENGINEERING (UNIVERSITY OF TEHRAN), vol. 36, no. 1 (75), pp. 47–62, 2002, [Online]. Available: https://sid.ir/paper/357336/en

Related Journal Papers