Kristof Karacs

Learn More
In spite of the impressive advances related to retinal prostheses, there is no imminent promise to make them soon available with a realistic performance to help navigating blind persons. In our new project, we are designing a Bionic Eyeglass that provides a wearable TeraOps visual computing power to advise visually impaired people in their daily life. In(More)
PURPOSE To optimize methods for positioning subretinal visual implants, customizing their cable length, guiding them to the predetermined retinal position, and evaluating their performance. METHODS Ten eyes of 10 patients (6 male, 4 female, mean age 46.4 years) were investigated before implantation of a subretinal visual implant. The structural(More)
Recognition of banknotes is a prevalent problem for blind and visually impaired people. The bionic eyeglass is a mobile platform that integrates several common visual detection and recognition functions. Relevant shapes are extracted from the image flow of the banknote shown to the mobile camera using adaptive thresholding and morphological shape filters.(More)
Although accessible pedestrian signals are more and more frequent at crosswalks in busy intersections, visually impaired people will not be able to get about independently until the infrastructure reaches full coverage on the routes they are using. In this paper, we present algorithms to detect and recognize pedestrian crosswalks developed in the framework(More)
This paper presents the basin tree diagrams of all hyper Bernoulli στ -shift rules for string lengths L = 3, 4, . . . , 8. These diagrams have revealed many global and time-asymptotic properties that we have subsequently proved to be true for all L < ∞. In particular, we have proved that local rule 60 has no Isles of Eden for all L, and that local rules 154(More)
Up until now there has been no available treatment for diseases causing the permanent impairment of retinal photoreceptors. Currently the development of the retinal prostheses is the earliest to promise a result that can be implemented in the clinical treatment of these patients. Implants with different operating principles and in various stages of progress(More)
Finding useful information in real world scenes is very important for many scene understanding tasks. Signs, scripts, information panels, and logos typically stand out from their environment for a human observer, but algorithmically locating them seems to depend on the actual context. We propose a hierarchical method that locates potentially interesting(More)
This dissertation (i) describes parallel histogram modification techniques with embedded morphological preprocessing methods within the CNN-UM framework, describes and illustrates how the implementation of the algorithm results in an adaptive multi-thresholding scheme when histogram modification is combined with embedded morphological processing at a finite(More)
  • 1