Three applications of pulse-coupled neural networks

摘要

Abstract: Image segmentation is one of the major applicationareas for Pulsed Coupled Neural Networks (PCNN).Previous research has shown that the ability of PCNN toignore minor variations in intensity and small spatialdiscontinuities in images is beneficial to imagesegmentation as well as image smoothing. This paperdescribes research and development projects in progressin which PCNN is used for the segmentation of threedifferent types of digital images. The software for thediagnosis of Pulmonary Embolism from VQ lung scans usesPCNN in single burst mode for segmenting perfusion andventilation images. The second project is attempting todetect ischemia by comparing 3D SPECT (Single PhotonEmission Computed Tomography) images of heart obtainedduring stress and rest conditions, respectively. Thethird application is a space science project whichdeals with the study of global auroral images obtainedfrom Ultraviolet Imager. The paper also describes anhardware implementation of PCNN as an electro-opticalchip.!5