I can't find any information on SDF and MACE save for a vague exert in Kinser's Image Operators books. Therefore I am dumbfounded. I can't understand what they do and what's their role in composite filters. Can somebody please explain them to me? Thanks.
Your question is allusive at that point: explanation of acronyms (SDF, MACE), need for composite filters... A starting point is matched spatial filter (MSF). To overcome its limitations, several versions have been proposed. David Casasent is a common denominatoir of the ones you consider.
For the SDF filer, my reference is:
- C. F. Hester and David Casasent, “Multivariant technique for multiclass pattern recognition,” Applied Optics, 1980
A technique for multiclass optical pattern recognition of different perspective views of an object is described. Each multiclass representation of an object is described as an orthonormal basis function expansion, and a single averaged matched spatial filter is then produced from a weighted linear combination of these functions. The technique is demonstrated for a terminal missile guidance application using IR tank imagery.
with comment in:
In a recent article, Hester and Casasent discussed an interesting technique in multiclass pattern recognition. They mentioned that other approaches to the construction of an orthonormal basis function set were possible and specifically suggested the possibility of using a Karhunen-Loéve expansion as an alternative to their own Gram-Schmidt procedure. It is the purpose of this Letter to recommend yet another alternative, the singular value decomposition (SVD), which has very convenient conceptual and numerical advantages, and to show how it may serve as a foundation for future extensions of the theory. The scope of the present discussion is restricted solely to the digital processing aspects of Ref. 1. It will begin with a brief review of the problem in the slightly modified matrix notation that is more compatible with the SVD technique that follows.
- Abhijit Mahalanobis, B. V. K. Vijaya Kumar, and David Casasent, Minimum average correlation energy filters, Applied Optics, 1987
The synthesis of a new category of spatial filters that produces sharp output correlation peaks with controlled peak values is considered. The sharp nature of the correlation peak is the major feature emphasized, since it facilitates target detection. Since these filters minimize the average correlation plane energy as the first step in filter synthesis, we refer to them as minimum average correlation energy filters. Experimental laboratory results from optical implementation of the filters are also presented and discussed