Publications

@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}

}

@article{gonzalez-castro_reliability_2017,

title = {Reliability of an automatic classifier for brain enlarged perivascular spaces burden and comparison with human performance},

author = {Víctor González-Castro and María del Carmen Valdés-Hernández and Francesca M Chappell and Paul A Armitage and Stephen Makin and Joanna M Wardlaw},

url = {https://portlandpress.com/clinsci/article/131/13/1465/71656/Reliability-of-an-automatic-classifier-for-brain},

year  = {2017},

date = {2017-01-01},

journal = {Clinical Science},

volume = {131},

number = {13},

pages = {1465–1481},

abstract = {Enlarged perivascular spaces (PVS) in the brain are associated with small vessel disease, poor cognition, and hypertension. This study proposes a fully automated method using a support vector machine (SVM) to classify PVS burden in the basal ganglia (BG) as low or high from T2-weighted MRI images. Three feature extraction techniques were evaluated, with the bag of visual words (BoW) approach achieving the highest accuracy (81.16%). The classifier's performance was comparable to that of trained human observers, and its predictions were clinically meaningful, as indicated by high AUC values (0.90–0.93). These findings suggest that automated PVS burden assessment could serve as a valuable clinical tool.},

note = {Publisher: Portland Press Ltd.},

keywords = {Bag of Visual Words, brain MRI, Discrete Wavelet Transform, Local Binary Patterns, machine learning, perivascular spaces, small vessel disease, support vector machine},

pubstate = {published},

tppubtype = {article}

}

@article{gonzalez-castro_texture_2015,

title = {Texture descriptors based on adaptive neighborhoods for classification of pigmented skin lesions},

author = {Víctor González-Castro and Johan Debayle and Yanal Wazaefi and Mehdi Rahim and Caroline Gaudy-Marqueste and Jean-Jacques Grob and Bernard Fertil},

url = {https://www.spiedigitallibrary.org/journals/Journal-of-Electronic-Imaging/volume-24/issue-6/061104/Texture-descriptors-based-on-adaptive-neighborhoods-for-classification-of-pigmented/10.1117/1.JEI.24.6.061104.short},

year  = {2015},

date = {2015-01-01},

journal = {Journal of Electronic Imaging},

volume = {24},

number = {6},

pages = {061104–061104},

abstract = {This paper proposes two texture descriptors for the automatic classification of skin lesions from dermoscopic images, focusing on color texture analysis. The first descriptor uses adaptive mathematical morphology (MM) and Kohonen self-organizing maps (SOM), while the second uses local binary patterns (LBP) with adaptive neighborhoods. Neither approach requires prior segmentation. The results show that the adaptive neighborhood-based LBP approach outperforms both nonadaptive versions of the proposed descriptors and dermatologists' visual predictions, as confirmed by receiver operating characteristic analysis.},

note = {Publisher: Society of Photo-Optical Instrumentation Engineers},

keywords = {Adaptive Neighborhoods, Dermoscopic Images, LBP, Local Binary Patterns, skin lesion classification, texture descriptors},

pubstate = {published},

tppubtype = {article}

}

@article{lopez_de_celis_evaluation_nodate,

title = {An evaluation of Cascade Object Detector and Support Vector Machine methods for People Detection using a RGB-Depth camera located in a zenithal position},

author = {Eduardo López de Celis and Óscar García-Olalla Olivera and Maite García-Ordás and Enrique Alegre},

url = {https://www.ehu.eus/documents/3444171/4484752/61.pdf},

abstract = {This project solves the problem of people detection 

using an RGB-Depth camera from a zenithal 

position. The detection process has been 

implemented for binary (head – no head) and 

multiclass approaches (short hair head, long hair 

head, ponytail and shoulders-no head). For this task, 

Histogram of Oriented Gradients (HOG) 

demonstrates to be a better feature descriptor than 

Local Binary Patterns (LBP). In the classification 

step, two models have been evaluated: SVM and 

Cascade Object Detector. Our experiments shown 

the better performance of SVM.},

keywords = {Cascade Object Detector, head detection, Histogram of Oriented Gradients, Local Binary Patterns, support vector machine},

pubstate = {published},

tppubtype = {article}

}