Image Segmentation and Edge Detection via Constrained Diffusion and Adaptive Morphology: a Cnn Approach to Bubble-debris Image Enhancement

In this paper, a cellular neural network (CNN) based locally adaptive scheme is presented for image segmentation and edge detection. It is shown that combining a constrained (linear or nonlinear) diffusion approach with adaptive morphology leads to a robust segmentation algorithm for an important class of image models. These images comprise of simple geometrical objects, each having a homogeneous gray-scale level and they might be overlapping. The background illumination is inhomogeneous, the objects are corrupted by additive Gaussian noise and possibly blurred by lowpass filtering type effects. Typically, this class has a multimodal (in most cases bimodal) image histogram and no special (easily exploitable) characteristics in the frequency domain. The synthesized analogic (analog and logic) CNN algorithm combines a diffusion-type filtering with a locally adaptive strategy based on estimating the first order (mean) and second order (variance) statistics. Both PDE and non-PDE related diffusion schemes are examined and compared in the CNN framework. It is shown that the proposed algorithm with various diffusion-type filters offers a more robust solution than some globally optimal thresholding schemes. All algorithmic steps are realized using nearest neighbor CNN templates. The VLSI implementation complexity and some robustness issues are carefully analyzed and discussed in detail. A number of tests has been completed within the frame of the so-called “bubble-debris” classification experiments on original and artificial gray-scale images.