Publications

@article{fidalgo_boosting_2018,

title = {Boosting image classification through semantic attention filtering strategies},

author = {Eduardo Fidalgo and Enrique Alegre and Víctor González-Castro and Laura Fernández-Robles},

url = {https://www.sciencedirect.com/science/article/pii/S0167865518302757},

year  = {2018},

date = {2018-01-01},

journal = {Pattern Recognition Letters},

volume = {112},

pages = {176–183},

abstract = {This paper presents three attention filtering methods based on saliency maps to enhance image classification using BoVW, SPM, and CNN features. The proposed strategies include AutoBlur for selecting the image signature's blurring factor and two SARF variants: one using Mean Shift segmentation and the other with a key point voting system. Experiments show that these methods improve classification performance in five datasets, outperforming baseline methods with BoVW, and achieving competitive results with SPM and CNN.},

note = {Publisher: North-Holland},

keywords = {Bag of Words, Image classification, Mean Shift, Saliency Map, support vector machine},

pubstate = {published},

tppubtype = {article}

}

@article{fidalgo_illegal_2018,

title = {Illegal activity categorisation in DarkNet based on image classification using CREIC method},

author = {Eduardo Fidalgo and Enrique Alegre and Victor González-Castro and Laura Fernández-Robles},

url = {https://link.springer.com/chapter/10.1007/978-3-319-67180-2_58},

year  = {2018},

date = {2018-01-01},

journal = {International Joint Conference SOCO’17-CISIS’17-ICEUTE’17 León, Spain, September 6–8, 2017, Proceeding 12},

pages = {600–609},

abstract = {This paper introduces TOIC (TOr Image Categories), a dataset of illegal images from the TOR network, and presents a method to classify them using a combination of Edge-SIFT and dense SIFT descriptors. These features are extracted from edge images created with the Compass Operator. The method employs a Bag of Visual Words model that fuses these descriptors early in the process to effectively detect and categorize illegal content. By selecting the optimal radius before calculating Edge-SIFT, the approach improves classification performance, achieving an accuracy of 92.49% on the TOIC dataset, and showing increased accuracy in tests on both TOIC and the Butterflies dataset. The method offers an efficient tool for identifying illegal content in the TOR network.},

note = {Publisher: Springer International Publishing},

keywords = {Bag of Visual Words, Edge-SIFT descriptors, Image classification, support vector machine, TOR},

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-based_2016,

title = {Texture-based classification for the automatic rating of the perivascular spaces in brain MRI},

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

url = {https://www.sciencedirect.com/science/article/pii/S1877050916311802},

year  = {2016},

date = {2016-01-01},

journal = {Procedia Computer Science},

volume = {90},

pages = {9–14},

abstract = {This paper investigates the classification of enlarged perivascular spaces (PVS) in the basal ganglia (BG) using texture features extracted from structural brain MRI. The texture is described through first-order statistics, co-occurrence matrix features, discrete wavelet transform coefficients (WSF and WCF), and local binary patterns (LBP). The texture features are classified using a Support Vector Machine (SVM). Experimental results show that WCF provides an accuracy of 80.03% in classifying the density of enlarged PVS.},

note = {Publisher: Elsevier},

keywords = {Discrete Wavelet Transform, local binary pattern, perivascular spaces, support vector machine, texture descriptors},

pubstate = {published},

tppubtype = {article}

}

@article{garcia-olalla_olivera_vitality_2013,

title = {Vitality assessment of boar sperm using an adaptive LBP based on oriented deviation},

author = {Oscar García-Olalla Olivera and Enrique Alegre and Laura Fernández-Robles and María Teresa García-Ordás},

url = {https://link.springer.com/chapter/10.1007/978-3-642-37410-4_6},

year  = {2013},

date = {2013-01-01},

journal = {Computer Vision-ACCV 2012 Workshops: ACCV 2012 International Workshops, Daejeon, Korea, November 5-6, 2012, Revised Selected Papers, Part I 11},

pages = {61–72},

abstract = {This paper proposes a new method to assess sperm vitality using a hybrid combination of local and global texture descriptors. A new adaptive local binary pattern (ALBP) descriptor, enhanced with oriented standard deviation information, is introduced as ALBPS, achieving better performance in sperm vitality assessment with an accuracy of 81.88%. In addition, the global description of sperm heads was evaluated with various classical texture algorithms, where the combination of Wavelet transform and Haralick feature extraction (WCF13) yielded the best results. The hybrid approach combining ALBPS and WCF13 achieved superior performance, with the best result being a F-Score of 0.886 and an accuracy of 85.63%. This method represents a significant improvement in sperm vitality classification.},

note = {Publisher: Springer Berlin Heidelberg},

keywords = {local binary pattern, Sperm Vitality, support vector machine, texture descriptors},

pubstate = {published},

tppubtype = {article}

}

@article{garcia-olalla_olivera_adaptive_2013,

title = {Adaptive local binary pattern with oriented standard deviation (ALBPS) for texture classification},

author = {Óscar García-Olalla Olivera and Enrique Alegre and Laura Fernández-Robles and María Teresa García-Ordás and Diego García-Ordás},

url = {https://link.springer.com/article/10.1186/1687-5281-2013-31},

year  = {2013},

date = {2013-01-01},

journal = {EURASIP journal on image and video processing},

volume = {2013},

pages = {1–11},

abstract = {This paper proposes a new texture description method combining local and global texture descriptors for image classification. The adaptive local binary pattern with oriented standard deviation (ALBPS) method provides enhanced local features, while the global description uses a wavelet transform-based descriptor, WCF13. These descriptors were combined with a support vector machine for classification, yielding high accuracy (85.63%) and F-score (0.886) for spermatozoa data and good results (84.45%) for the KTH-TIPS 2a dataset. The hybrid approach outperformed previous methods.},

note = {Publisher: Springer International Publishing},

keywords = {adaptive local binary pattern, hybrid feature extraction, image analysis, local binary pattern, spermatozoa assessment, support vector machine, texture classification, wavelet trasform},

pubstate = {published},

tppubtype = {article}

}

@article{alegre_vitality_2011,

title = {Vitality assessment of boar sperm using N concentric squares resized (NCSR) texture descriptor in digital images},

author = {Enrique Alegre and María Teresa García-Ordás and Victor González-Castro and S Karthikeyan},

url = {https://link.springer.com/chapter/10.1007/978-3-642-21257-4_67},

year  = {2011},

date = {2011-01-01},

journal = {Pattern Recognition and Image Analysis: 5th Iberian Conference, IbPRIA 2011, Las Palmas de Gran Canaria, Spain, June 8-10, 2011. Proceedings 5},

pages = {540–547},

abstract = {Two new textural descriptor, named N Concentric Squares Resized (NCSR) and N Concentric Squares Histogram (NCSH), have been proposed. These descriptors were used to classify 472 images of alive spermatozoa heads and 376 images of dead spermatozoa heads. The results obtained with these two novel descriptors have been compared with a number of classical descriptors such as Haralick, Pattern Spectrum, WSF, Zernike, Flusser and Hu. The feature vectors computed have been classified using kNN and a backpropagation Neural Network. The error rate obtained for NCSR with N = 11 was of 23.20% outperforms the rest of descriptors. Also, the area under the ROC curve (AUC) and the values observed in the ROC curve indicates the performance of the proposed descriptor is better than the others texture description methods.},

note = {Publisher: Springer Berlin Heidelberg},

keywords = {local binary pattern, Sperm Vitality, support vector machine, texture descriptors},

pubstate = {published},

tppubtype = {article}

}

@article{fernandez-robles_svm_nodate,

title = {SVM APPROACH TO CLASSIFY BOAR ACROSOME INTEGRITY OF A MULTI-FEATURES SURF},

author = {Laura Fernández-Robles and Óscar García-Olalla Olivera and María Teresa García-Ordás and Diego García-Ordás and Enrique Alegre},

url = {https://d1wqtxts1xzle7.cloudfront.net/44449818/SVM_approach_to_classify_boar_acrosome_i20160405-28158-qszl8d-libre.pdf?1459894369=&response-content-disposition=inline%3B+filename%3DSVM_Approach_to_Classify_Boar_Acrosome_I.pdf&Expires=1739795517&Signature=Tgnu3YoKmzyQiRloeYT95Z4ufJAMUtL~2z~sVtWh4x0OwtjsDwwxq7cUYjl-q5NxrhAJJNz3b7f7YchGOHb6p7lf48EUqtmL1Cjm1mI6YY59k3-ds8J53mCRa0SdXtjjZa0MvchGa2Aqbqx3pt5Ep6v5To7Trx3aKfElmzjdaSP7yKZxPa~b92YaH02HFDTQkx8UFEf6TuCoitK-mz4On4xw-6-RfHwdh37FtKePaXdKxv~sHwmvwVWlOn~yaNIPTO1sl3X8LT9zuUU~8yHltm8xUlFuOzWXwgAe8bMmYMWr6HwY-GG7ExpJQj43FmIa6XXflt7MlJRIuAzSgSo~Lw__&Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA},

abstract = {This paper presents an approach to improve the classification of invariant local feature descriptors in images of boar spermatozoa heads using Support Vector Machine (SVM). The method involves detecting interest points with SURF and classifying the acrosome as intact or damaged. The approach focuses on classifying the whole head rather than individual points, leveraging the fact that a head typically has more distinctive points of its own class than doubtful ones. The results show a hit rate of 90.91%, indicating that this method could be an effective alternative for classifying invariant local features.},

keywords = {Image classification, Image Recognition, Invariant Local Features, support vector machine, SURF},

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}

}