A neural system design for CDF operations

Conjugate directional filtering (CDF) is a method proposed by us recently. By using CDF, two direction-filtered results in conjugate directions can be merged into one image that shows the maximum linear features in the two conjugate directions. However, we only reported the CDF concepts and operations in our previous paper, without considerations in how to implement this method. In this paper, we report the progressive result of our CDF study, which shows that a neural system can be used to implement the CDF operations. Two neural network designs are proposed based on whether a program that conducts directional filtering should be included. Trial work on a synthetic model processed using this neural system is also reported.