Links Contact

^ Back to Calculation-Page ^

How to use this page

General remarks
  • Fill in the appropriate data in the form-fields of the previous page. We already filled in an example that should work.
  • After submitting your job, our server will try to fetch your images, convert them into an internal floating-point format, and than start the calculations.
  • You can decide to watch the process of the calculations by observing the log-file, or just to wait for your result, which will be send back to you as soon as they become available. If the log-file fails to update automatically, you have to push your "RELOAD"-button.
  • After your calculations are finished, the results are stored at our server for further reference. However, after one or two days, the data will no longer be available on our server.
When things go wrong
  • Most problems occur in accessing your data by our server. Be shure to give a correct URL. You can check your URL by opening the location in your own browser. If your browser loads your image, the URL should be fine. (If our server still can't fetch your data, please contact us.)
  • The algorithms have been designed to be fairly bullet-proof, but if you do not enter correct values, you won't get any sensible results.
  • This server is used also other purposes. If the load-average exceeds 3.0, this service is temporarily suspended.
Specific remarks
  • You should limit the size of your input images to 256x256 pixel.
  • A scalespace description is created and then used to detect important image parts. Here's an example:

     - Input Example  -

    Input image
    (Namibian rock-painting, photo courtesy of Svenja Falk)

    Data is analyzed from coarse scales down to finer scales; the found segmentation borders are drawn into a slightly enlarged picture of your original data, which will be sent back to you in several output-formats:

     - Example of Output-Formats -

    Example of possible Outputs

    Since the segmentation is based solely on image intensities, do not expect good results if your image is mainly structured by texture-boundaries. Preprocess you images in this case.

© 1994-2000 - all rights reserved.