![]() ![]() In general we advise to initially select a wide range of feature types and scales. Note how the filter fits to the smallest edges at the very low sigma value and only finds the rough cell outlines at a high sigma. The following image provides an example of the edge filter computed with 3 different sigma values. If you feel that a certain value of the sigma would be particularly well suited to your data, you can also add your own sigmas in the last column, as shown above in red. Filters with larger sigmas can thus pull in information from larger neighborhoods, but average out the fine details. The scales correspond to the sigma of the Gaussian which is used to smooth the image before application of the filter.
0 Comments
Leave a Reply. |
Details
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |