A 2‐D IIR neural hybrid filter for image processing
Mitsuji Muneyasu, S. Tsujii, Takao Hinamoto · Electronics and Communications in Japan (Part III Fundamental Electronic Science) · 1994
Abstract A two‐dimensional (2‐D) IIR neural hybrid (2DINH) filter is proposed for image processing. This 2DINH filter consists of the cascade connection of a 2‐D IIR linear filter followed by a neural filter. The proposed filter can be applied to smoothing for the images corrupted with Gaussian noise and/or impulsive noise and to edge detection for the images corrupted with Gaussian noise. The parameters of a neural filter are adjustable by a learning algorithm to adapt itself to the property of an image to be processed. Finally, some examples are given to illustrate the utility of the proposed filter.