Adrián Galdrán Education At Present Fourth Year of PhD Studies, Tecnalia Research Corporation, Zamudio Technological Park, Bizkaia. Computer Vision Area, PhD Topics: Image Processing, Image Restoration, Color Correction, Variational Techniques in Image Processing

2010-2011 First Year of PhD Studies Master on Mathematical Modelization, Statistics and Computation, Tecnalia Research Corporation - University of Basque Country UPV/EHU, Best Master Project Honours. 2008-2009 BCAM - Basque Center for Applied Mathematics, Zamudio Technological Park, Bizkaia. Advanced Aspects in Applied Mathematics

2008-2009 Master on Mathematical Investigation, University of Valencia/Polytechnical University of Valencia, Valencia. Scholarship recipient of ’la Caixa’ Foundation, Grant for Master Studies in Spain

2002-2008 Degree on Mathematics, University of Valencia, Valencia, 7.2/10. Five years degree, including several subjects on the degree of Informatics, on Computer Graphics and Computational Geometry. Assistant Scholar at the Department of Geometry and Topology of the Faculty of Mathematics in the last course.

2000-2002 Secondary School, IES 8 de Marzo, Alicante. Exceptional Award of Baccalaureate course at a Regional Level.

Publications Journal Papers Title Automatic Red-Channel Underwater Image Restoration Authors Adrián Galdrán, David Pardo, Artzai Picón Journal Journal of Visual Image Communication and Representation, 2014 (accepted) Description Underwater images typically exhibit color distortion and low contrast as a result of the exponential decay that light suffers as it travels. Moreover, colors associated to different wavelengths have different attenuation rates, being the red wavelength the one that attenuates the fastest. To restore underwater images, we propose a Red Channel method, where colors associated to short wavelengths are recovered, as expected for underwater images, leading to a recovery of the lost contrast.

Artekale 40, 3F – 48005 Bilbo, Bizkaia H +34 666 146191 • B [email protected] https://sites.google.com/site/adriangaldran/

1/4

Conferences Title A Variational Framework for Single Image Dehazing Authors Adrián Galdrán, David Pardo, Artzai Picón Journal Proceedings of ECCV 2014 - 4th Color and Photometry in Computer Vision Workshop, 2014 Description Images captured under adverse weather conditions, such as haze or fog, typically exhibit low contrast and faded colors, which may severely limit the visibility within the scene. Unveiling the image structure under the haze layer and recovering vivid colors out of a single image remains a challenging task, since the degradation is depth-dependent and conventional methods are unable to handle this problem. We propose to extend a well-known perception-inspired variational framework for the task of single image dehazing. The main modification consists on the replacement of the value used by this framework for the grey-world hypothesis by an estimation of the mean of the clean image. This allows us to devise a variational method that requires no estimate of the depth structure of the scene, performing a spatially-variant contrast enhancement that effectively removes haze from far away regions. Experimental results show that our method competes well with other state-of-the-art methods in typical benchmark images, while outperforming current image dehazing methods in more challenging scenarios. Title Minisymposium: Projects in technology centers of the Basque Country Mathematical Image Segmentation. Variational and Level Set Techniques Authors Adrián Galdrán, David Pardo, Artzai Picón Journal Proceedings of the RSME Conference on Transfer and Industrial Mathematics, 2011 Description We focus on the deep understanding and implementation of existing variational techniques for image segmentation. In the field of Variational Image Segmentation, mathematical methods coming from the area of numerical analysis and PDE can be combined with statistical and probabilistic techniques, yielding powerful generalistic algorithms that in many aspects overcome other previous techniques in the area. In here we provide a review on some basic topics in the area, that configure the starting point of our work.

Artekale 40, 3F – 48005 Bilbo, Bizkaia H +34 666 146191 • B [email protected] https://sites.google.com/site/adriangaldran/

2/4

Presentations Title A Variational Framework for Single Image Dehazing Authors Adrián Galdrán, David Pardo, Artzai Picón Congress ECCV 2014 - 4th Color and Photometry in Computer Vision Workshop, Zurich, Swiss, 2014 Description Presentation of a new variational scheme that is suitable for image dehazing tasks. Title Image Restoration Techniques on Hazy and Underwater Environments Authors Adrián Galdrán, David Pardo, Artzai Picón Congress Mathematics and Applications Days (V-MAD 4), Valparaiso, Chile, 2014 Description Description of our recent work on underwater image restoration, inspired on recent algorithms that work for images acquired under hazy conditions. Title Distance Dependent Image Degradation. Restoration Algorithms and Applications to Atmospheric and Underwater image enhancement Authors Adrián Galdrán, David Pardo, Artzai Picon Congress BCAM-UPV Applied Mathematics Colloquium, 2013 Description Description of the problem of imaging through scattering and attenuating media, such as haze, water and tissue, and related techniques to tackle the problem of image restoration in this context. Title Minisymposium: Projects in technology centers of the Basque Country Mathematical Image Segmentation. Variational and Level Set Techniques. Authors Adrián Galdrán, David Pardo, Artzai Picon Congress RSME Conference on Transfer and Industrial Mathematics, 2011 Description Description of existing variational techniques for image segmentation, and their level set implementation. Title Free-Form Techniques for the Deformation of the Geometry in Aerodynamical Shape Optimization Authors Adrián Galdrán, Francisco Palacios Congress MTM Workshop (BCAM) 2010 Description Description of recent advances in the field of shape optimization, and free-form tools for the deformation of the geometry.

Master Thesis - Master on Mathematical Modelization, Statistics and Computation Title Level Set and Variational Image Segmentation Supervisors - David Pardo, Dpt. of Matemática Aplicada, Estadística e Investigación Operativa, Universidad del País Vasco - Artzai Picón, Computer Vision Area, Tecnalia Research Corporation Description We studied modern Variational Image Segmentation techniques using Partial Differential Equations (PDE’s), with special emphasis on the Level Set method. The main idea of these techniques is to define an energy functional, whose minimum produces a suitable decomposition of the image.

Artekale 40, 3F – 48005 Bilbo, Bizkaia H +34 666 146191 • B [email protected] https://sites.google.com/site/adriangaldran/

3/4

Master Thesis - Master on Mathematical Investigation Title Curvas de Hodógrafo Pitagórico. Clasificación y Métodos de Construcción Supervisors Juan Monterde García-Pozuelo, Dpt. Geometria i Topologia, Universitat de València Description We studied some theoretical and practical aspects of a special type of curves useful in the CAD fiel, called Pythagorean Hodograph Curves. Their main property is that its arc-length function is not the square of a polynomial, but a polynomial, allowing for more efficient computations of some important geometrical quantities. This work was awarded with Best Master Project Honours.

Languages Spanish English Valencià Euskara French

Mother Tongue Fluent Fluent Intermediate Intermediate

Full Degree in Official Language School of Alicante (B2-equivalent) Mitjà Official Certificate(B2-equivalent) Habe Bi Maila (B2-equivalent) Four courses taken during Secondary Education

Main Computer skills High Level Programming Tools Python Advanced: Regular Working Tool for Numerical Mathematical Problems, Optimization, Image Processing, etc.

Matlab Advanced: Regular Working Tool for Numerical Mathematical Problems, Optimization, Image Processing, etc.

Mathematica Intermediate: Regular Working Tool for Geometry Processing and Representation

Low-Level Languages Java Basic:One-Quatrimester Course in the Master’s Degree C/C++/CImg Intermediate: Some experience during the Degree. Some self-study. Occasionally involved in medium-size projects during Graduate studies.

Others Latex Advanced: As a tool for Mathematical documents generation Miscellaneous User Level:Windows, Office: Word, Excel

Artekale 40, 3F – 48005 Bilbo, Bizkaia H +34 666 146191 • B [email protected] https://sites.google.com/site/adriangaldran/

4/4