®®®® SIIA Público

Título del libro: 2015 International Conference On Computer Communication And Informatics (iccci)
Título del capítulo: Mexican Archaeological Image Retrieval Based on Object Matching and a Local Descriptor

Autores UNAM:
MANUEL CEDILLO HERNANDEZ; FRANCISCO JAVIER GARCIA UGALDE;
Autores externos:

Idioma:

Año de publicación:
2015
Palabras clave:

Content-based image retrieval; indexing image; SURF descriptor; local descriptor


Resumen:

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.


Entidades citadas de la UNAM: