Jan Erik Solem is part of a research team in applied mathematics that is working with image analysis and computer vision. In his dissertation he shows how computers can be made, through mathematical processes, to create three-dimensional models of objects or persons on the basis of regular photographs.
Simply put, it’s a matter of calculating where the camera was positioned in relation to the object and then doing the geometry, according to Jan Erik Solem.
“For faces it’s possible in principle to create 3D data on the basis of a single photograph, but most often we have worked with 5-10 still photos or with film sequences.”
The technology is applicable to a number of fields, as Jan Erik Solem sees it.
“Much of our research is geared to automating work at the computer. In city planning, for example, and architecture many hours of work are devoted to creating 3D models manually. If that process can be simplified, there will be incredible amounts of money saved. Another conceivable area of use is in gaming, where this technology would make it possible to put objects into the virtual world by photographing them,” he says.
Jan Erik Solem himself hopes to soon be living proof that the results of his dissertation can be commercialized. He has started a company called Polar Rose, which has developed a technology for recognizing faces based on his research findings. The productthe Web-based search enginewill be the first in the world that can search for faces and not text.
The search engine will soon undergo testing by a number of beta-users, and roughly by year’s end it will be launched full scale, according to Jan Erik Solem.
“Since there is no such search service in existence today, it’s going to be really exciting to see how it is received. And if it’s a success, then we’ll be saddled with the luxury problem of competing with giants like Google, Microsoft, and Yahoo.”
Jan Erik Solem will defend his dissertation Variational Problems and Level Set Methods in Computer Vision-Theory and Applications on Friday, September 29, at 1:15 p.m. The venue will be Östra Varvsgatan 9A (Submarine Hall), Hall U:301, Malmö.
Sanna Camitz | alfa
Scientists use artificial neural networks to predict new stable materials
18.09.2018 | University of California - San Diego
ORNL-developed technology streamlines computational science projects
17.09.2018 | DOE/Oak Ridge National Laboratory
Thin-film solar cells made of crystalline silicon are inexpensive and achieve efficiencies of a good 14 percent. However, they could do even better if their shiny surfaces reflected less light. A team led by Prof. Christiane Becker from the Helmholtz-Zentrum Berlin (HZB) has now patented a sophisticated new solution to this problem.
"It is not enough simply to bring more light into the cell," says Christiane Becker. Such surface structures can even ultimately reduce the efficiency by...
A study in the journal Bulletin of Marine Science describes a new, blood-red species of octocoral found in Panama. The species in the genus Thesea was discovered in the threatened low-light reef environment on Hannibal Bank, 60 kilometers off mainland Pacific Panama, by researchers at the Smithsonian Tropical Research Institute in Panama (STRI) and the Centro de Investigación en Ciencias del Mar y Limnología (CIMAR) at the University of Costa Rica.
Scientists established the new species, Thesea dalioi, by comparing its physical traits, such as branch thickness and the bright red colony color, with the...
Scientists have succeeded in observing the first long-distance transfer of information in a magnetic group of materials known as antiferromagnets.
An international team of researchers has mapped Nemo's genome, providing the research community with an invaluable resource to decode the response of fish to...
Graphene is considered a promising candidate for the nanoelectronics of the future. In theory, it should allow clock rates up to a thousand times faster than today’s silicon-based electronics. Scientists from the Helmholtz Zentrum Dresden-Rossendorf (HZDR) and the University of Duisburg-Essen (UDE), in cooperation with the Max Planck Institute for Polymer Research (MPI-P), have now shown for the first time that graphene can actually convert electronic signals with frequencies in the gigahertz range – which correspond to today’s clock rates – extremely efficiently into signals with several times higher frequency. The researchers present their results in the scientific journal “Nature”.
Graphene – an ultrathin material consisting of a single layer of interlinked carbon atoms – is considered a promising candidate for the nanoelectronics of the...
03.09.2018 | Event News
27.08.2018 | Event News
17.08.2018 | Event News
18.09.2018 | Materials Sciences
18.09.2018 | Materials Sciences
18.09.2018 | Information Technology