Person: López Molina, Carlos
Loading...
Email Address
person.page.identifierURI
Birth Date
Research Projects
Organizational Units
Job Title
Last Name
López Molina
First Name
Carlos
person.page.departamento
Estadística, Informática y Matemáticas
person.page.instituteName
ORCID
0000-0002-0904-9834
person.page.upna
810097
Name
28 results
Search Results
Now showing 1 - 10 of 28
Publication Embargo Non-symmetric over-time pooling using pseudo-grouping functions for convolutional neural networks(Elsevier, 2024) Ferrero Jaurrieta, Mikel; Paiva, Rui; Cruz, Anderson; Callejas Bedregal, Benjamin; Miguel Turullols, Laura de; Takáč, Zdenko; López Molina, Carlos; Bustince Sola, Humberto; Estadística, Informática y Matemáticas; Estatistika, Informatika eta Matematika; Institute of Smart Cities - ISCConvolutional Neural Networks (CNNs) are a family of networks that have become state-of-the-art in several fields of artificial intelligence due to their ability to extract spatial features. In the context of natural language processing, they can be used to build text classification models based on textual features between words. These networks fuse local features to generate global features in their over-time pooling layers. These layers have been traditionally built using the maximum function or other symmetric functions such as the arithmetic mean. It is important to note that the order of input local features is significant (i.e. the symmetry is not an inherent characteristic of the model). While this characteristic is appropriate for image-oriented CNNs, where symmetry might make the network robust to image rigid transformations, it seems counter-productive for text processing, where the order of the words is certainly important. Our proposal is, hence, to use non-symmetric pooling operators to replace the maximum or average functions. Specifically, we propose to perform over-time pooling using pseudo-grouping functions, a family of non-symmetric aggregation operators that generalize the maximum function. We present a construction method for pseudo-grouping functions and apply different examples of this family to over-time pooling layers in text-oriented CNNs. Our proposal is tested on seven different models and six different datasets in the context of engineering applications, e.g. text classification. The results show an overall improvement of the models when using non-symmetric pseudo-grouping functions over the traditional pooling function.Publication Open Access A framework for radial data comparison and its application to fingerprint analysis(Elsevier, 2016) Marco Detchart, Cedric; Cerrón González, Juan; Miguel Turullols, Laura de; López Molina, Carlos; Bustince Sola, Humberto; Galar Idoate, Mikel; Automatika eta Konputazioa; Institute of Smart Cities - ISC; Automática y Computación; Universidad Pública de Navarra / Nafarroako Unibertsitate PublikoaThis work tackles the comparison of radial data, and proposes comparison measures that are further applied to fingerprint analysis. First, we study the similarity of scalar and non-scalar radial data, elaborated on previous works in fuzzy set theory. This study leads to the concepts of restricted radial equivalence function and Radial Similarity Measure, which model the perceived similarity between scalar and vectorial pieces of radial data, respectively. Second, the utility of these functions is tested in the context of fingerprint analysis, and more specifically, in the singular point detection. With this aim, a novel Template-based Singular Point Detection method is proposed, which takes advantage of these functions. Finally, their suitability is tested in different fingerprint databases. Different Similarity Measures are considered to show the flexibility offered by these measures and the behaviour of the new method is compared with well-known singular point detection methods.Publication Open Access Image feature extraction using OD-monotone functions(Springer, 2018) Marco Detchart, Cedric; López Molina, Carlos; Fernández Fernández, Francisco Javier; Pagola Barrio, Miguel; Bustince Sola, Humberto; Estatistika, Informatika eta Matematika; Institute of Smart Cities - ISC; Estadística, Informática y MatemáticasEdge detection is a basic technique used as a preliminary step for, e.g., object extraction and recognition in image processing. Many of the methods for edge detection can be fit in the breakdown structure by Bezdek, in which one of the key parts is feature extraction. This work presents a method to extract edge features from a grayscale image using the so-called ordered directionally monotone functions. For this purpose we introduce some concepts about directional monotonicity and present two construction methods for feature extraction operators. The proposed technique is competitive with the existing methods in the literature. Furthermore, if we combine the features obtained by different methods using penalty functions, the results are equal or better results than stateof-the-art methods.Publication Open Access Evaluation of near-infrared hyperspectral imaging for the assessment of potato processing aptitude(Frontiers Media, 2022) López Maestresalas, Ainara; López Molina, Carlos; Oliva Lobo, Gil Alfonso; Jarén Ceballos, Carmen; Ruiz de Galarreta, José Ignacio; Peraza Alemán, Carlos Miguel; Arazuri Garín, Silvia; Ingeniaritza; Estatistika, Informatika eta Matematika; Institute on Innovation and Sustainable Development in Food Chain - ISFOOD; Ingeniería; Estadística, Informática y MatemáticasThe potato (Solanum tuberosum L.) is the world's fifth most important staple food with high socioeconomic relevance. Several potato cultivars obtained by selection and crossbreeding are currently on the market. This diversity causes tubers to exhibit different behaviors depending on the processing to which they are subjected. Therefore, it is interesting to identify cultivars with specific characteristics that best suit consumer preferences. In this work, we present a method to classify potatoes according to their cooking or frying as crisps aptitude using NIR hyperspectral imaging (HIS) combined with a Partial Least Squares Discriminant Analysis (PLS-DA). Two classification approaches were used in this study. First, a classification model using the mean spectra of a dataset composed of 80 tubers belonging to 10 different cultivars. Then, a pixel-wise classification using all the pixels of each sample of a small subset of samples comprised of 30 tubers. Hyperspectral images were acquired using fresh-cut potato slices as sample material placed on a mobile platform of a hyperspectral system in the NIR range from 900 to 1,700 nm. After image processing, PLS-DA models were built using different pre-processing combinations. Excellent accuracy rates were obtained for the models developed using the mean spectra of all samples with 90% of tubers correctly classified in the external dataset. Pixel-wise classification models achieved lower accuracy rates between 66.62 and 71.97% in the external validation datasets. Moreover, a forward interval PLS (iPLS) method was used to build pixel-wise PLS-DA models reaching accuracies above 80 and 71% in cross-validation and external validation datasets, respectively. Best classification result was obtained using a subset of 100 wavelengths (20 intervals) with 71.86% of pixels correctly classified in the validation dataset. Classification maps were generated showing that false negative pixels were mainly located at the edges of the fresh-cut slices while false positive were principally distributed at the central pith, which has singular characteristics.Publication Open Access From restricted equivalence functions on Ln to similarity measures between fuzzy multisets(IEEE, 2023) Ferrero Jaurrieta, Mikel; Takáč, Zdenko; Rodríguez Martínez, Iosu; Marco Detchart, Cedric; Bernardini, Ángela; Fernández Fernández, Francisco Javier; López Molina, Carlos; Bustince Sola, Humberto; Estadística, Informática y Matemáticas; Estatistika, Informatika eta MatematikaRestricted equivalence functions are well-known functions to compare two numbers in the interval between 0 and 1. Despite the numerous works studying the properties of restricted equivalence functions and their multiple applications as support for different similarity measures, an extension of these functions to an n-dimensional space is absent from the literature. In this paper, we present a novel contribution to the restricted equivalence function theory, allowing to compare multivalued elements. Specifically, we extend the notion of restricted equivalence functions from L to L n and present a new similarity construction on L n . Our proposal is tested in the context of color image anisotropic diffusion as an example of one of its many applications.Publication Open Access Twofold binary image consensus for medical imaging meta-analysis(Springer, 2018) López Molina, Carlos; Sánchez Ruiz de Gordoa, Javier; Zelaya Huerta, María Victoria; Baets, Bernard de; Estadística, Informática y Matemáticas; Estatistika, Informatika eta MatematikaIn the field of medical imaging, ground truth is often gathered from groups of experts, whose outputs are generally heterogeneous. This procedure raises questions on how to compare the results obtained by automatic algorithms to multiple ground truth items. Secondarily, it raises questions on the meaning of the divergences between experts. In this work, we focus on the case of immunohistochemistry image segmentation and analysis. We propose measures to quantify the divergence in groups of ground truth images, and we observe their behaviour. These measures are based upon fusion techniques for binary images, which is a common example of non-monotone data fusion process. Our measures can be used not only in this specific field of medical imagery, but also in any task related to meta-quality evaluation for image processing, e.g. ground truth validation or expert rating.Publication Open Access A framework for active contour initialization with application to liver segmentation in MRI(Springer, 2022) Mir Torres, Arnau; Antunes dos Santos, Felipe; Fernández Fernández, Francisco Javier; López Molina, Carlos; Estadística, Informática y Matemáticas; Estatistika, Informatika eta MatematikaObject segmentation is a prominent low-level task in image processing and computer vision. A technique of special relevance within segmentation algorithms is active contour modeling. An active contour is a closed contour on an image which can be evolved to progressively fit the silhouette of certain area or object. Active contours shall be initialized as a closed contour at some position of the image, further evolving to precisely fit to the silhouette of the object of interest. While the evolution of the contour has been deeply studied in literature [5, 11], the study of strategies to define the initial location of the contour is rather absent from it. Typically, such contour is created as a small closed curve around an inner position in the object. However, literature contains no general-purpose algorithms to determine those inner positions, or to quantify their fitness. In fact, such points are frequently set manually by human experts, hence turning the segmentation process into a semi-supervised one. In this work, we present a method to find inner points in relevant object using spatial-tonal fuzzy clustering. Our proposal intends to detect dominant clusters of bright pixels, which are further used to identify candidate points or regions around which active contours can be initialized.Publication Open Access Hyperspectral imaging using notions from type-2 fuzzy sets(Springer, 2019) López Maestresalas, Ainara; Miguel Turullols, Laura de; López Molina, Carlos; Arazuri Garín, Silvia; Bustince Sola, Humberto; Jarén Ceballos, Carmen; Ingeniería; Ingeniaritza; Estadística, Informática y Matemáticas; Estatistika, Informatika eta Matematika; Universidad Pública de Navarra / Nafarroako Unibertsitate PublikoaFuzzy set theory has developed a prolific armamentarium of mathematical tools for each of the topics that has fallen within its scope. One of such topics is data comparison, for which a range of operators has been presented in the past. These operators can be used within the fuzzy set theory, but can also be ported to other scenarios in which data are provided in various representations. In this work, we elaborate on notions for type-2 fuzzy sets, specifically for the comparison of type-2 fuzzy membership degrees, to create function comparison operators. We further apply these operators to hyperspectral imaging, in which pixelwise data are provided as functions over a certain energy spectra. The performance of the functional comparison operators is put to the test in the context of in-laboratory hyperspectral image segmentation.Publication Open Access Operador de comparación de elementos multivaluados basado en funciones de equivalencia restringida(Universidad de Málaga, 2021) Castillo López, Aitor; López Molina, Carlos; Fernández Fernández, Francisco Javier; Sesma Sara, Mikel; Bustince Sola, Humberto; Estadística, Informática y Matemáticas; Estatistika, Informatika eta MatematikaEn este trabajo proponemos un nuevo enfoque del algoritmo de clustering gravitacional basado en lo que Einstein considero su 'mayor error': la constante cosmológica. De manera similar al algoritmo de clustering gravitacional, nuestro enfoque está inspirado en principios y leyes del cosmos, y al igual que ocurre con la teoría de la relatividad de Einstein y la teoría de la gravedad de Newton, nuestro enfoque puede considerarse una generalización del agrupamiento gravitacional, donde, el algoritmo de clustering gravitacional se recupera como caso límite. Además, se desarrollan e implementan algunas mejoras que tienen como objetivo optimizar la cantidad de iteraciones finales, y de esta forma, se reduce el tiempo de ejecución tanto para el algoritmo original como para nuestra versión.Publication Open Access Multiscale edge detection using first-order derivative of anisotropic Gaussian kernels(Springer, 2019) Wang, Gang; López Molina, Carlos; Baets, Bernard de; Estadística, Informática y Matemáticas; Estatistika, Informatika eta MatematikaSpatially scaled edges are ubiquitous in natural images. To better detect edges with heterogeneous widths, in this paper, we propose a multiscale edge detection method based on first-order derivative of anisotropic Gaussian kernels. These kernels are normalized in scale-space, yielding a maximum response at the scale of the observed edge, and accordingly, the edge scale can be identified. Subsequently, the maximum response and the identified edge scale are used to compute the edge strength. Furthermore, we propose an adaptive anisotropy factor of which the value decreases as the kernel scale increases. This factor improves the noise robustness of small-scale kernels while alleviating the anisotropy stretch effect that occurs in conventional anisotropic methods. Finally, we evaluate our method on widely used datasets. Experimental results validate the benefits of our method over the competing methods.
- «
- 1 (current)
- 2
- 3
- »