Deep learning technologies are getting noticed out of the academic circles. A new post at Tecnalia inspiring blog provides a detailed analysis of these novel techniques. On that post, we summarize some key elements of the deep learning technology and give some insight on relevant companies and applications. Taking into consideration current growing figures of deep learning, the technology will be a key piece on current and future business.
Last month we updated our deep learning servers into ubuntu 16.04 LTS Xenial. In this post we provide a summary of the steps we followed to have Theano, Caffe and Tensorflow under ubuntu 16.04. As ubuntu 16.04 is not yet supported by main deep learning environment and even CUDA drivers, we provide a step by step guideline to be able to build a deep learning environment with ubuntu 16.04. This is also valid for installing into 14.04 version just skipping the compiling files adaption. We have also included some of the configuration/test files described in this summary at link 1. Install prerequisites: This install prerequisites required to build the different dependencies and frameworks. sudo apt-get update sudo apt-get upgrade sudo apt-get install build-essential sudo apt-get autoremove sudo apt-get install git git config --global user.name $MYNAME git config --global user.email $MYMAIL 2. Install nvidia graphics driver: Download drivers Nvidia driver Start [...]
Our colleague at Tecnalia Computer Vision, Adrián Galdrán has successfully presented his PhD dissertation at the Applied Mathematics Department of the University of the Basque Country. This work has been co-tutored among this University and Tecnalia. The work, entitled “Visibility Recovery on Images Acquired in Attenuating Media. Application to Underwater, Fog, and Mammographic Imaging”, presents novel variational algorithms to restore the information contained on degraded images acquired under attenuating conditions such as, underwater, haze or human tissue. This restoration plays an essential role for the performance of ulterior image analysis and understanding algorithms. The developed algorithms have been already applied to natural, underwater, medical and steel process images both for restoration purposes and to improve the performance of analysis algorithms. Congratulations!
The Computer Vision group has been awarded with the International Excellence Group (GEI) recognition by Tecnalia. At Tecnalia, GEI recognition is given to highly specialized teams that outstand both on academic research (PhD Thesis, patents exploited by 3rd parties, relevant research papers…) and on market oriented approach (International R&D contracts, development of technological assets… ). The existence of these groups at Tecnalia potentiates focused applied research with greater outcomes to industry. Tecnalia evaluation committee highlighted the international contracts with different transnational companies of our group and the international awards received by the team. We would like to thank our collaborators and companies that along these years have trusted in the group.
Tecnalia actively collaborates with Erasmus Mundus Joint Master Degree CO·SI (Colour in Science and Industry). COSI / COlour in Science and Industry / is a two-year (120 ECTS) Erasmus+ Joint Master Degree, aiming to train the next generation of highly-skilled industrial experts in applied colour science, in various cutting-edge industries (photonics, optics, spectral imaging, multimedia technologies, computer graphics and vision) in a diverse range of sectors (including multimedia, health care, cosmetic, automotive, food-processing) bridging a talent gap in the industry where colour experts are in high demand. The 2 area of focus are spectral technologies and applied colour imaging. COSI is brought to you by a world leading university-business cooperation of 4 European universities (University Jean Monnet, University of Granada, University of Eastern Finland and Gjovik University College), 5 Asian universities and 15 industrial leaders across the globe. Call for Applications for 2016-2018 intake is now open! Apply [...]
Alzheimer´s disease causes symptoms such as memory loss, disorientation or mood swings in those suffering from it, but, what exactly changes in the brain and how can we improve its detection? Magnetic resonance imaging (MRI) opens the possibility of examining the structure, the metabolism or the functionality of the brain and thereby, numerous analysis tools have been developed to understand and extract the information they carry. One of the most common techniques is “Voxel-based morphometry” or VBM (Ashburner and Friston, 2000), used to identify brain regional atrophy by statistically comparing a group of patients with a group of controls. Figure 1 describes the steps involved in a VBM analysis. Figure 1: Steps of a VBM analysis. VBM studies to date have exploited T1-weighted MRIs, which were designed to enhance the MRI signal contrast between grey and white matter tissues (Figure 2). They are therefore suitable for detecting [...]
The Biopool platform is a biological sample search and location service for a biobanks network. Biopool allows sharing different collections of histological images as well as its associated clinical and histological information which is available at member biobanks. The use of this interconnected network of information sources has great potential in the field of medical research, education and as a tool for diagnosis support. At present, researchers must contact several biobanks in order to find a biobank which can provide samples of the diseases to carry out their research. There is no agile mechanism that eases these searches. Biopool´s aim is to change this procedure by providing a tool that will allow the search for biological samples which is similar to that used as a reference by the search engine. Biopool will provide the set of relevant samples ranked by similarity as well as their location and diagnosis. [...]
Common search engines like Google or Bing still just rely on text-based analysis, providing real time results with great accuracy. However, sometimes, the page rank implemented by these search engines does not provide the web-pages that we are looking for. Sergio Rodriguez-Vaamonde, researcher at Tecnalia Computer Vision Area, under the supervision of Prof. Lorenzo Torresani from Dartmouth College and in collaboration with Microsoft Research have proved that image information can be included in text-based search engines to increase the search accuracy. In order to test this hypothesis, Sergio developed a search engine that analyses the page rank returned by a text search and extracts the visual information associated to each web-page image. The algorithm uses computer vision and artificial intelligence techniques to properly describe and categorize the images and use this information to re-rank the results of the text search engine. Performed test on the TREC datasets reveal [...]