Abstract
Humans recognize images by a process called foveation. Our eyes gather information about different points of interest within the image and assimilate this information to identify the image. The foveation points are generally the corners, and sometimes, the edges of segments within an image. The pulse-coupled neural network (PCNN) has the inherent ability to segment an image, where the corners and edges of the segments are similar to foveation points. In this paper, the theory of foveation using a PCNN is presented, along with some examples. Also shown is that the technique of foveation through a PCNN can be used in pattern recognition using a fuzzy syntactic approach. An application to handwritten character recognition is also presented.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have