TY - GEN
T1 - Mexican archaeological image retrieval based on object matching and a local descriptor
AU - Cedillo-Hernandez, Manuel
AU - Garcia-Ugalde, Francisco Javier
AU - Cedillo-Hernandez, Antonio
AU - Nakano-Miyatake, Mariko
AU - Perez-Meana, Hector
N1 - Publisher Copyright:
© 2015 IEEE.
PY - 2015/8/21
Y1 - 2015/8/21
N2 - Content-based image retrieval (CBIR) is a hard task which consists in retrieving similar content from a large multimedia database. In the literature, in order to extract descriptors from the images the CBIR techniques use several low-level features such as color, texture, shape, contours, among others. In the recent years, several local descriptors based on the detection of feature points have been used to retrieve the most similar images with different geometric and photometric characteristics. In this paper we propose a CBIR technique that involves the combination of a local descriptor obtained from the Speeded Up Robust Feature (SURF) algorithm together with an effective and fast object matching operation in order to improve the search speed and the retrieval accuracy related to the Mexican archaeological imaging. In order to reduce the computational complexity of the proposed method, Quarter Common Intermediate Format (QCIF) is used previous of computing the SURF descriptor. To measure the performance of the proposed technique the precision and recall metrics are used. The experimental results show the accuracy of the proposed CBIR technique applied to a data base of Mexican culture images that are captured by several environmental conditions and different acquisition equipment.
AB - Content-based image retrieval (CBIR) is a hard task which consists in retrieving similar content from a large multimedia database. In the literature, in order to extract descriptors from the images the CBIR techniques use several low-level features such as color, texture, shape, contours, among others. In the recent years, several local descriptors based on the detection of feature points have been used to retrieve the most similar images with different geometric and photometric characteristics. In this paper we propose a CBIR technique that involves the combination of a local descriptor obtained from the Speeded Up Robust Feature (SURF) algorithm together with an effective and fast object matching operation in order to improve the search speed and the retrieval accuracy related to the Mexican archaeological imaging. In order to reduce the computational complexity of the proposed method, Quarter Common Intermediate Format (QCIF) is used previous of computing the SURF descriptor. To measure the performance of the proposed technique the precision and recall metrics are used. The experimental results show the accuracy of the proposed CBIR technique applied to a data base of Mexican culture images that are captured by several environmental conditions and different acquisition equipment.
KW - Content-based image retrieval
KW - SURF descriptor
KW - indexing image
KW - local descriptor
UR - http://www.scopus.com/inward/record.url?scp=84953790816&partnerID=8YFLogxK
U2 - 10.1109/ICCCI.2015.7218071
DO - 10.1109/ICCCI.2015.7218071
M3 - Contribución a la conferencia
AN - SCOPUS:84953790816
T3 - 2015 International Conference on Computer Communication and Informatics, ICCCI 2015
BT - 2015 International Conference on Computer Communication and Informatics, ICCCI 2015
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 5th International Conference on Computer Communication and Informatics, ICCCI 2015
Y2 - 8 January 2015 through 10 January 2015
ER -