Image Processing using Pulse-Coupled Neural Networks

Embedding Topical Elements of Parallel Programming, Computer Graphics, and Artificial Intelligence across the Undergraduate CS Required Courses

“…A quick glance will indicate whether the resulting image is reconstructed, or scrambled! AI is introduced into parallel processing in the context of parallelizing AI paradigms such as Pulse-Coupled Neural Networks (PCNN) [19], a biologically inspired model for computer vision and image preprocessing. Figure 12, for example, shows eight frames from an echocardiographic cineloop, or "movie", which have been borderenhanced using the PCNN.…”

Medical Image Segmentation Using Artificial Neural Networks

“…A model of the cat's visual cortex was proposed by Eckhorn et al (1989). Over the past decade, PCNNs have been used for a variety of image processing applications such as segmentation, feature and face extraction, motion detection, and noise reduction (Lindblad and Kinser, 2005). PCNN consists of a pool of neurons where each neuron corresponds to a pixel in the image receiving its local information and the stimuli from its neighbouring neurons.…”

Pattern recognition using pulse-coupled neural networks and discrete Fourier transforms

“…V F and V L are normalizing constants and M and W represent the constant synaptic weights. M and W are computed by using the inverse square rule [10]:…”

“…Important research in the 80's and 90's led to the establishment of a general model for PCNN [3]. Such models proved to be highly applicable in the field of image processing, a series of optimal procedures being developed for contour detection and especially image segmentation [10].…”