Publications
2019
1.
Olivera, Óscar García-Olalla; Fernández-Robles, Laura; Alegre, Enrique; Castejón-Limas, Manuel; Fidalgo, Eduardo
Boosting texture-based classification by describing statistical information of gray-levels differences Artículo de revista
En: Sensors, vol. 19, no 5, pp. 1048, 2019, (Publisher: MDPI).
Resumen | Enlaces | BibTeX | Etiquetas: CLOSIB, Local Binary Patterns, Statistica Information of Gray-Levels Differences, texture classification, texture description, Visual Sensors
@article{garcia-olalla_olivera_boosting_2019,
title = {Boosting texture-based classification by describing statistical information of gray-levels differences},
author = {Óscar García-Olalla Olivera and Laura Fernández-Robles and Enrique Alegre and Manuel Castejón-Limas and Eduardo Fidalgo},
url = {https://www.mdpi.com/1424-8220/19/5/1048},
year = {2019},
date = {2019-01-01},
journal = {Sensors},
volume = {19},
number = {5},
pages = {1048},
abstract = {This paper introduces a new texture descriptor booster, CLOSIB (Complete Local Oriented Statistical Information Booster), designed to enhance the discriminative power of texture descriptors like LBP. By using statistical information from image gray-level differences, the method improves texture classification. Variants such as Half-CLOSIB (H-CLOSIB) and Multi-scale CLOSIB (M-CLOSIB) offer increased efficiency and robustness. The method was tested on datasets like KTH TIPS, UIUC, USPTex, and JAFFE, showing improved classification accuracy when combined with LBP-based descriptors. Comparisons with recent algorithms show that CLOSIB variants provide competitive results.},
note = {Publisher: MDPI},
keywords = {CLOSIB, Local Binary Patterns, Statistica Information of Gray-Levels Differences, texture classification, texture description, Visual Sensors},
pubstate = {published},
tppubtype = {article}
}
This paper introduces a new texture descriptor booster, CLOSIB (Complete Local Oriented Statistical Information Booster), designed to enhance the discriminative power of texture descriptors like LBP. By using statistical information from image gray-level differences, the method improves texture classification. Variants such as Half-CLOSIB (H-CLOSIB) and Multi-scale CLOSIB (M-CLOSIB) offer increased efficiency and robustness. The method was tested on datasets like KTH TIPS, UIUC, USPTex, and JAFFE, showing improved classification accuracy when combined with LBP-based descriptors. Comparisons with recent algorithms show that CLOSIB variants provide competitive results.
2018
2.
Olivera, Óscar García-Olalla; Alegre, Enrique; Fernández-Robles, Laura; Fidalgo, Eduardo; Saikia, Surajit
Textile retrieval based on image content from cdc and webcam cameras in indoor environments Artículo de revista
En: Sensors, vol. 18, no 5, pp. 1329, 2018, (Publisher: MDPI).
Resumen | Enlaces | BibTeX | Etiquetas: Content-based Image Retrieval, Textile Localization, Textile Retrieval, texture description, Texture Retrieval, Visual Sensors
@article{garcia-olalla_olivera_textile_2018,
title = {Textile retrieval based on image content from cdc and webcam cameras in indoor environments},
author = {Óscar García-Olalla Olivera and Enrique Alegre and Laura Fernández-Robles and Eduardo Fidalgo and Surajit Saikia},
url = {https://www.mdpi.com/1424-8220/18/5/1329},
year = {2018},
date = {2018-01-01},
urldate = {2018-01-01},
journal = {Sensors},
volume = {18},
number = {5},
pages = {1329},
abstract = {This paper presents a method for textile-based image retrieval, useful for law enforcement to identify evidence by matching textiles in real-world scenes. The approach uses MSER on high-pass filtered RGB, HSV, and Hue channels to extract textile regions. HOG and HCLOSIB are combined for feature description and correlation distance to match the query textile patch with candidate regions. A new dataset, TextilTube, consisting of 1913 labeled textile regions in 67 classes, is introduced. Experimental results show 84.94% success in the top 40 matches and 37.44% precision for the first match, outperforming current deep learning methods.},
note = {Publisher: MDPI},
keywords = {Content-based Image Retrieval, Textile Localization, Textile Retrieval, texture description, Texture Retrieval, Visual Sensors},
pubstate = {published},
tppubtype = {article}
}
This paper presents a method for textile-based image retrieval, useful for law enforcement to identify evidence by matching textiles in real-world scenes. The approach uses MSER on high-pass filtered RGB, HSV, and Hue channels to extract textile regions. HOG and HCLOSIB are combined for feature description and correlation distance to match the query textile patch with candidate regions. A new dataset, TextilTube, consisting of 1913 labeled textile regions in 67 classes, is introduced. Experimental results show 84.94% success in the top 40 matches and 37.44% precision for the first match, outperforming current deep learning methods.