Embedded double matching of local descriptors for a fast automatic recognition of real-world objects

T. Alqaisi, D. Gledhill, J. I. Olszewska

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

9 Citations (Scopus)

Abstract

In this paper, we present a new approach for matching local descriptors such as Scale Invariant Feature Transform (SIFT) ones in order to recognize image objects quickly and reliably. The proposed method first computes the Hausdorff distance combined with the City-Block distance to match the two sets of the extracted keypoints from the goal and data images, respectively. Then, the matched points are involved into an embedded pairing process, leading to a double matching which is more discriminant for the object recognition purpose as demonstrated on real-world standard databases.

LanguageEnglish
Title of host publication2012 IEEE International Conference on Image Processing, ICIP 2012 - Proceedings
Pages2385-2388
Number of pages4
DOIs
Publication statusPublished - 2012
Event19th IEEE International Conference on Image Processing - Lake Buena Vista, United States
Duration: 30 Sep 20123 Oct 2012
Conference number: 19

Conference

Conference19th IEEE International Conference on Image Processing
Abbreviated titleICIP 2012
CountryUnited States
CityLake Buena Vista
Period30/09/123/10/12

Fingerprint

Object recognition
Mathematical transformations

Cite this

Alqaisi, T., Gledhill, D., & Olszewska, J. I. (2012). Embedded double matching of local descriptors for a fast automatic recognition of real-world objects. In 2012 IEEE International Conference on Image Processing, ICIP 2012 - Proceedings (pp. 2385-2388). [6467377] https://doi.org/10.1109/ICIP.2012.6467377
Alqaisi, T. ; Gledhill, D. ; Olszewska, J. I. / Embedded double matching of local descriptors for a fast automatic recognition of real-world objects. 2012 IEEE International Conference on Image Processing, ICIP 2012 - Proceedings. 2012. pp. 2385-2388
@inproceedings{c6d36be9a2bd4dd4bafd5a88e97fc51a,
title = "Embedded double matching of local descriptors for a fast automatic recognition of real-world objects",
abstract = "In this paper, we present a new approach for matching local descriptors such as Scale Invariant Feature Transform (SIFT) ones in order to recognize image objects quickly and reliably. The proposed method first computes the Hausdorff distance combined with the City-Block distance to match the two sets of the extracted keypoints from the goal and data images, respectively. Then, the matched points are involved into an embedded pairing process, leading to a double matching which is more discriminant for the object recognition purpose as demonstrated on real-world standard databases.",
keywords = "City-Block Distance, Euclidean Distance, Feature Matching, Hausdorff Distance, Interest Points, Object Recognition, SIFT, Similarity Measure",
author = "T. Alqaisi and D. Gledhill and Olszewska, {J. I.}",
year = "2012",
doi = "10.1109/ICIP.2012.6467377",
language = "English",
isbn = "9781467325332",
pages = "2385--2388",
booktitle = "2012 IEEE International Conference on Image Processing, ICIP 2012 - Proceedings",

}

Alqaisi, T, Gledhill, D & Olszewska, JI 2012, Embedded double matching of local descriptors for a fast automatic recognition of real-world objects. in 2012 IEEE International Conference on Image Processing, ICIP 2012 - Proceedings., 6467377, pp. 2385-2388, 19th IEEE International Conference on Image Processing, Lake Buena Vista, United States, 30/09/12. https://doi.org/10.1109/ICIP.2012.6467377

Embedded double matching of local descriptors for a fast automatic recognition of real-world objects. / Alqaisi, T.; Gledhill, D.; Olszewska, J. I.

2012 IEEE International Conference on Image Processing, ICIP 2012 - Proceedings. 2012. p. 2385-2388 6467377.

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

TY - GEN

T1 - Embedded double matching of local descriptors for a fast automatic recognition of real-world objects

AU - Alqaisi, T.

AU - Gledhill, D.

AU - Olszewska, J. I.

PY - 2012

Y1 - 2012

N2 - In this paper, we present a new approach for matching local descriptors such as Scale Invariant Feature Transform (SIFT) ones in order to recognize image objects quickly and reliably. The proposed method first computes the Hausdorff distance combined with the City-Block distance to match the two sets of the extracted keypoints from the goal and data images, respectively. Then, the matched points are involved into an embedded pairing process, leading to a double matching which is more discriminant for the object recognition purpose as demonstrated on real-world standard databases.

AB - In this paper, we present a new approach for matching local descriptors such as Scale Invariant Feature Transform (SIFT) ones in order to recognize image objects quickly and reliably. The proposed method first computes the Hausdorff distance combined with the City-Block distance to match the two sets of the extracted keypoints from the goal and data images, respectively. Then, the matched points are involved into an embedded pairing process, leading to a double matching which is more discriminant for the object recognition purpose as demonstrated on real-world standard databases.

KW - City-Block Distance

KW - Euclidean Distance

KW - Feature Matching

KW - Hausdorff Distance

KW - Interest Points

KW - Object Recognition

KW - SIFT

KW - Similarity Measure

UR - http://www.scopus.com/inward/record.url?scp=84875854576&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2012.6467377

DO - 10.1109/ICIP.2012.6467377

M3 - Conference contribution

SN - 9781467325332

SP - 2385

EP - 2388

BT - 2012 IEEE International Conference on Image Processing, ICIP 2012 - Proceedings

ER -

Alqaisi T, Gledhill D, Olszewska JI. Embedded double matching of local descriptors for a fast automatic recognition of real-world objects. In 2012 IEEE International Conference on Image Processing, ICIP 2012 - Proceedings. 2012. p. 2385-2388. 6467377 https://doi.org/10.1109/ICIP.2012.6467377