Browsing AI Memos (1959 - 2004) by Author "Nishihara, H.K."

Now showing items 1-5 of 5

    • CARTOON: A Biologically Motivated Edge Detection Algorithm 

      Richards, W.; Nishihara, H.K.; Dawson, B. (1982-06-01)
      Caricatures demonstrate that only a few significant "edges" need to be captured to convey the meaning of a complex pattern of image intensities. The most important of these "edges" are image intensity changes arising ...

    • Hidden Clues in Random Line Stereograms 

      Nishihara, H.K.; Poggio, T. (1983-08-01)
      Successful fusion of random-line stereograms with breaks in the vernier acuity range has been previously interpreted to suggest that the interpolation process underlying hyperacuity is parallel and preliminary to ...

    • PRISM: A Practical Real-Time Imaging Stereo Matcher 

      Nishihara, H.K. (1984-05-01)
      A binocular-stereo-matching algorithm for making rapid visual range measurements in noisy images is described. This technique is developed for application to problems in robotics where noise tolerance, reliability, and ...

    • Representation and Recognition of the Spatial Organization of Three Dimensional Shapes 

      Marr, D.; Nishihara, H.K. (1977-05-01)
      The human visual process can be studied by examining the computational problems associated with deriving useful information from retinal images. In this paper, we apply this approach to the problem of representing ...

    • Representation and Recognition of the Spatial Organization of Three-Dimensional 

      Marr, D.; Nishihara, H.K. (1976-08-01)
      A method is given for representing 3-D shapes. It is based on a hierarchy of stick figures (called 3-D models), where each stick corresponds to an axis in the shape's generalized cone representation. Although the ...