peretz@gradient.cis.upenn.edu (Samuel R. Peretz) (06/06/91)
Does anyone out there do any work on recognition of "general" features, i.e. features that can only be described in terms of general properties? I am working on designing a network which will be able to look at bitmapped images (they've been thresholded, so they're binary), and determine whether there is any kind of general feature present (e.g. a "blob", a "band", a "donut", etc.). If anyone has any references on work such as this, I'd be very grateful. Two other peripheral questions: I need a good image-processing reference book; I am particularly interested in one that deals with thresholding of grey-scale images as a preprocessing technique. Also, I was wondering if there exists any kind of book with numerical-type algorithms in Common Lisp--something along the same lines as the "Numerical Recipes in C" type of books. --Sam Peretz <=======================================================> < Samuel R. Peretz > < 126 Anatomy/Chemistry Bldg. \ / > < University of Pennsylvania ------- > < Inst. for Neurological Sciences | 0 0 | > < (215) 898-8048 | V | > < peretz@grad1.cis.upenn.edu | === | > < aka sam@retina.anatomy.upenn.edu ------- > < aka srp@vision5.anatomy.upenn.edu > <=======================================================> <=======================================================> < Samuel R. Peretz >