@conference {martinez2019benchmarking, title = {Benchmarking Machine-Learning-Based Object Detection on a UAV and Mobile Platform}, booktitle = {2019 IEEE Wireless Communications and Networking Conference (WCNC)}, year = {2019}, pages = {1{\textendash}6}, publisher = {IEEE}, organization = {IEEE}, author = {Martinez-Alpiste, Ignacio and Pablo Casaseca-de-la-Higuera and Jose-Maria Alcaraz-Calero and Grecos, Christos and Wang, Qi} } @conference {752, title = {Bias Correction for Non-Stationary Noise Filtering in MRI}, booktitle = {2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI)}, year = {2018}, month = {2018}, address = {Washington DC}, author = {Tomasz Pieciak and I{\~n}aki Rabanillo-Viloria and Santiago Aja-Fern{\'a}ndez} } @article {873, title = {A blood orange computer vision sorting system}, year = {2017}, abstract = {To have a proper sorting system with a low error rate can be very useful in automatic packaging of products. Furthermore, physical dimensions and shape are important in sorting and sizing of fruits and vegetables. In this paper Iranian orange (blood orange) are considered to present an automatic mass sorting system with low error rate using image processing coupled with an adaptive neurofuzzy inference system (ANFIS). Linear regression analysis was used to compare results and an efficient algorithm was designed and implemented in MatLab. This algorithm is able to measure area, eccentricity, perimeter, length/area, red, green, and blue RGB components, width, contrast, texture, width/area, width/length, roughness and length. In ANFIS model, samples were divided into two sets: 70\% for training and 30\% for testing. Best ANFIS, linear and nonlinear regression models, yielded values of the coefficient of determination (R2), sum squared error (SSE), and mean squared error (MSE) of 0.989, 21.46, 1.65 (ANFIS), 0.91, 1156.69, 12.05 (linear) and 0.88, 1538.10, 15.86 (nonlinear), respectively. Based on results, ANFIS model showed clearly better capability for mass prediction compared to both linear and nonlinear regression. A prototype for an automatic non-intrusive orange mass sorting system is depicted to conclude.}, doi = {https://doi.org/10.1049/cp.2017.0167}, url = {https://digital-library.theiet.org/content/conferences/10.1049/cp.2017.0167}, author = {Sabzi, Sajad and Yousef Abbaspour-Gilandeh and J I Arribas} } @proceedings {543, title = {Blind Estimation of Spatially Variant Noise in GRAPPA MRI}, year = {2015}, pages = {SuAT7.4}, abstract = {

The reconstruction process in multiple coil MRI scanners makes the noise features in the final magnitude image become non-stationary, i.e. the variance of noise becomes position-dependent. Therefore, most noise estimators proposed in the literature cannot be used in multiple-coil acquisitions. This effect is augmented when parallel imaging methods, such as GRAPPA, are used to increase the acquisition rate.

In this work we propose a new technique that allows the estimation of the spatially variant maps of noise from the GRAPPA reconstructed signal when only one single image is available and no additional information is provided. Other estimators in the literature need extra information that is not always available, which has supposed an important limitation in the usage of noise models for GRAPPA. The proposed approach uses a homomorphic separation of the spatially variant noise in two terms: a stationary noise term and one low frequency signal that correspond to the x-dependent variance of noise. The non-stationary variance of noise is estimated by a low pass filtering. The noise term is obtained via prior wavelet decomposition. Results in real and synthetic experiments evidence the suitability of the simplification used and the good performance of the proposed methodology.

}, author = {Santiago Aja-Fern{\'a}ndez and Gonzalo Vegas-S{\'a}nchez-Ferrero} } @article {garmendia2011beta, title = {Beta blocker therapy modifies circadian rhythm acute myocardial infarction}, journal = {International journal of cardiology}, volume = {147}, number = {2}, year = {2011}, pages = {316{\textendash}317}, publisher = {Elsevier}, author = {Jose Ramon Garmendia-Leiza and Jesus Maria Andres-de-Llano and Julio Ardura-Fernández and Juan Bautista Lopez-Messa and Carlos Alberola-Lopez and Pablo Casaseca-de-la-Higuera} } @inbook {tristan2009bias, title = {Bias of least squares approaches for diffusion tensor estimation from array coils in DT{\textendash}MRI}, booktitle = {Medical Image Computing and Computer-Assisted Intervention{\textendash}MICCAI 2009}, year = {2009}, pages = {919{\textendash}926}, publisher = {Springer Berlin Heidelberg}, organization = {Springer Berlin Heidelberg}, author = {Antonio Trist{\'a}n-Vega and Carl-Fredik Westin and Santiago Aja-Fern{\'a}ndez} } @inbook {tristan2009blurring, title = {On the Blurring of the Funk{\textendash}Radon Transform in Q{\textendash}Ball Imaging}, booktitle = {Medical Image Computing and Computer-Assisted Intervention{\textendash}MICCAI 2009}, year = {2009}, pages = {415{\textendash}422}, publisher = {Springer Berlin Heidelberg}, organization = {Springer Berlin Heidelberg}, author = {Antonio Trist{\'a}n-Vega and Santiago Aja-Fern{\'a}ndez and Carl-Fredik Westin} } @article {de2003biometric, title = {Biometric identification systems}, journal = {Signal Processing}, volume = {83}, number = {12}, year = {2003}, pages = {2539{\textendash}2557}, publisher = {Elsevier}, author = {Rodrigo de Luis-Garc{\'\i}a and Carlos Alberola-Lopez and Aghzout, Otman and Juan Ruiz-Alzola} } @inbook {martin2002bayesian, title = {A Bayesian Approach to in vivo Kidney Ultrasound Contour Detection Using Markov Random Fields}, booktitle = {Medical Image Computing and Computer-Assisted Intervention{\textemdash}MICCAI 2002}, year = {2002}, pages = {397{\textendash}404}, publisher = {Springer}, organization = {Springer}, author = {Marcos Martin-Fernandez and Carlos Alberola-Lopez} }