To identify the intrinsic connections within different layers of area 17 of the cat visual cortex we studied the initial neurons labelled by horseradish peroxidase retrograde axonal transport in serial sections. A computer model of visual neural networks (Dudkin et al, 1995 Proceedings of SPIE 122) has been specially developed in these studies to classify cortical neurons according to their specific anatomic features. There are two main stages of the recognition process in this model: feature selection by nonlinear neural operators and classification (clustering) connected with algorithms of cluster analysis. In the first stage, the primary image processing and segmentation are performed by interactive algorithms, which allow us to form several primary image descriptions and to extract the basic description elements of the cell. From these elements, a feature vector consisting of 17 normalised measures is extracted. In the second stage of the recognition process several algorithms are used to cluster the cells according to the feature vectors extracted. It was possible to group these vectors into compact clusters and to associate each group of vectors with a certain type of cells (pyramidal, spiny, and smooth stellate cells). These results are part of the task of creating a computer image data base and 3-D reconstruction of the cortico-cortical connections in the visual system.
