Publications

@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}

}

@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}

}

@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}

}