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.
2014
2.
González-Castro, Víctor; Debayle, Johan; Pinoli, Jean-Charles
Color Adaptive Neighborhood Mathematical Morphology and its application to pixel-level classification Artículo de revista
En: Pattern Recognition Letters, vol. 47, pp. 50–62, 2014, (Publisher: North-Holland).
Resumen | Enlaces | BibTeX | Etiquetas: Adaptive Structuring Elements, Color Images, image processing, mathematical morphology, texture classification
@article{gonzalez-castro_color_2014,
title = {Color Adaptive Neighborhood Mathematical Morphology and its application to pixel-level classification},
author = {Víctor González-Castro and Johan Debayle and Jean-Charles Pinoli},
url = {https://www.sciencedirect.com/science/article/pii/S016786551400021X},
year = {2014},
date = {2014-01-01},
journal = {Pattern Recognition Letters},
volume = {47},
pages = {50–62},
abstract = {This paper explores spatially adaptive Mathematical Morphology (MM) for color images by generalizing the General Adaptive Neighborhood Image Processing (GANIP) approach. It introduces Color Adaptive Neighborhoods (CAN) as adaptive structuring elements (ASE) for morphological operations. The method, applied to various color spaces, outperforms other ASEs in preserving object borders and color transitions. The adaptive morphological operators are further applied to classify color texture images.},
note = {Publisher: North-Holland},
keywords = {Adaptive Structuring Elements, Color Images, image processing, mathematical morphology, texture classification},
pubstate = {published},
tppubtype = {article}
}
This paper explores spatially adaptive Mathematical Morphology (MM) for color images by generalizing the General Adaptive Neighborhood Image Processing (GANIP) approach. It introduces Color Adaptive Neighborhoods (CAN) as adaptive structuring elements (ASE) for morphological operations. The method, applied to various color spaces, outperforms other ASEs in preserving object borders and color transitions. The adaptive morphological operators are further applied to classify color texture images.
3.
González-Castro, Víctor; Debayle, Johan; Curic, Vladimir
Pixel classification using general adaptive neighborhood-based features Artículo de revista
En: 2014 22nd International Conference on Pattern Recognition, pp. 3750–3755, 2014, (Publisher: IEEE).
Resumen | Enlaces | BibTeX | Etiquetas: Adaptive Neighborhoods, mathematical morphology, pixel classification, texture classification
@article{gonzalez-castro_pixel_2014,
title = {Pixel classification using general adaptive neighborhood-based features},
author = {Víctor González-Castro and Johan Debayle and Vladimir Curic},
url = {https://ieeexplore.ieee.org/abstract/document/6977356},
year = {2014},
date = {2014-01-01},
journal = {2014 22nd International Conference on Pattern Recognition},
pages = {3750–3755},
abstract = {This paper presents a new descriptor using General Adaptive Neighborhoods (GANs) for classifying pixels in texture images. GANs define a spatial region around each pixel that fits its local structure, and pixel features are derived from region-based and intensity-based measurements. The method outperforms others, achieving 97.25% accuracy in five-class classification and high area under curve values in binary classifications using the VisTex database.},
note = {Publisher: IEEE},
keywords = {Adaptive Neighborhoods, mathematical morphology, pixel classification, texture classification},
pubstate = {published},
tppubtype = {article}
}
This paper presents a new descriptor using General Adaptive Neighborhoods (GANs) for classifying pixels in texture images. GANs define a spatial region around each pixel that fits its local structure, and pixel features are derived from region-based and intensity-based measurements. The method outperforms others, achieving 97.25% accuracy in five-class classification and high area under curve values in binary classifications using the VisTex database.
2013
4.
Olivera, Óscar García-Olalla; Alegre, Enrique; Fernández-Robles, Laura; García-Ordás, María Teresa; García-Ordás, Diego
Adaptive local binary pattern with oriented standard deviation (ALBPS) for texture classification Artículo de revista
En: EURASIP journal on image and video processing, vol. 2013, pp. 1–11, 2013, (Publisher: Springer International Publishing).
Resumen | Enlaces | BibTeX | Etiquetas: adaptive local binary pattern, hybrid feature extraction, image analysis, local binary pattern, spermatozoa assessment, support vector machine, texture classification, wavelet trasform
@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}
}
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.
2012
5.
Olivera, Óscar García-Olalla; García-Ordás, María Teresa; García-Ordás, Diego; Fernández-Robles, Laura; Alegre, Enrique
Vitality assessment of boar sperm using n concentric squares resized and local binary pattern in gray scale images Artículo de revista
En: XXXIII Jornadas de Automatica, 2012.
Resumen | Enlaces | BibTeX | Etiquetas: Biomedical Image, local binary pattern, Sperm Vitality, texture classification
@article{garcia-olalla_vitality_2012,
title = {Vitality assessment of boar sperm using n concentric squares resized and local binary pattern in gray scale images},
author = {Óscar García-Olalla Olivera and María Teresa García-Ordás and Diego García-Ordás and Laura Fernández-Robles and Enrique Alegre},
url = {https://www.researchgate.net/profile/Oscar-Garcia-Olalla/publication/268519830_Vitality_assessment_of_boar_sperm_using_N_Concentric_Squares_resized_and_Local_binary_pattern_in_gray_scale_images/links/546f374b0cf24af340c07a96/Vitality-assessment-of-boar-sperm-using-N-Concentric-Squares-resized-and-Local-binary-pattern-in-gray-scale-images.pdf},
year = {2012},
date = {2012-01-01},
urldate = {2012-01-01},
journal = {XXXIII Jornadas de Automatica},
abstract = {This work introduces a new texture descriptor combining Local Binary Pattern (LBP) and N-concentric squares resized (NCSR) to classify boar spermatozoa as dead or alive using grayscale images. The classifier used was Support Vector Machine (SVM), and the best performance (78.67% hit rate) was achieved with NCSR of 50 features and LBP with 16 neighbors. This result outperforms previous methods in the field, making it a promising tool for automating sperm vitality classification in veterinary practices.},
keywords = {Biomedical Image, local binary pattern, Sperm Vitality, texture classification},
pubstate = {published},
tppubtype = {article}
}
This work introduces a new texture descriptor combining Local Binary Pattern (LBP) and N-concentric squares resized (NCSR) to classify boar spermatozoa as dead or alive using grayscale images. The classifier used was Support Vector Machine (SVM), and the best performance (78.67% hit rate) was achieved with NCSR of 50 features and LBP with 16 neighbors. This result outperforms previous methods in the field, making it a promising tool for automating sperm vitality classification in veterinary practices.
6.
González-Castro, Víctor; Alegre, Enrique; Olivera, Óscar García-Olalla; Fernández-Robles, Laura; García-Ordás, Maria Teresa
Adaptive pattern spectrum image description using euclidean and geodesic distance without training for texture classification Artículo de revista
En: IET Computer Vision, vol. 6, no 6, pp. 581–589, 2012, (Publisher: IET Digital Library).
Resumen | Enlaces | BibTeX | Etiquetas: adaptive methods, euclidean distance, geodesic distance, mathematical morphology, pattern spectrum, texture classification
@article{gonzalez-castro_adaptive_2012,
title = {Adaptive pattern spectrum image description using euclidean and geodesic distance without training for texture classification},
author = {Víctor González-Castro and Enrique Alegre and Óscar García-Olalla Olivera and Laura Fernández-Robles and Maria Teresa García-Ordás},
url = {https://digital-library.theiet.org/doi/10.1049/iet-cvi.2012.0098},
year = {2012},
date = {2012-01-01},
journal = {IET Computer Vision},
volume = {6},
number = {6},
pages = {581–589},
abstract = {Mathematical morphology can be used to extract a shape–size distribution called pattern spectrum (PS) with texture description purposes. However, the structuring element (SE) used to compute it does not vary along the image; and therefore it does not capture its geometrical variations. The author's proposal consists of computing an SE at each pixel whose size and shape varies with two distance criterions: an Geodesic distance and a Euclidean distance, in order to fit the texture as well as possible. Combining the Geodesic and the Euclidean descriptors as just one descriptor, the classification results of several textures from the VisTex and Brodatz database show that this approach outperforms the classical PS, the Geodesic and the Euclidean descriptors separately and, in contrast with other adaptive methods, it does not require previous training.},
note = {Publisher: IET Digital Library},
keywords = {adaptive methods, euclidean distance, geodesic distance, mathematical morphology, pattern spectrum, texture classification},
pubstate = {published},
tppubtype = {article}
}
Mathematical morphology can be used to extract a shape–size distribution called pattern spectrum (PS) with texture description purposes. However, the structuring element (SE) used to compute it does not vary along the image; and therefore it does not capture its geometrical variations. The author's proposal consists of computing an SE at each pixel whose size and shape varies with two distance criterions: an Geodesic distance and a Euclidean distance, in order to fit the texture as well as possible. Combining the Geodesic and the Euclidean descriptors as just one descriptor, the classification results of several textures from the VisTex and Brodatz database show that this approach outperforms the classical PS, the Geodesic and the Euclidean descriptors separately and, in contrast with other adaptive methods, it does not require previous training.