The Hopfield neural network has been widely applied in many areas. Its
highly interconnected structure of neurons is not only very effective
in computational complexity but also very fault tolerant. Such neural
networks have been used as analog computational networks for solving
optimization problems. The low-level image processing of edge detectio
n can also be regarded as an optimization problem. This paper presents
an edge detection algorithm using a Hopfield neural network. This alg
orithm utilizes a concept that is different from conventional differen
tiation operators, such as the Sobel and Laplacian. In this algorithm,
an image is mapped to a Hopfield neural network, which is completely
depicted by an energy function. In other words, an image is described
by a set of interconnected neurons. Every pixel in the image is repres
ented by a neuron, which is connected to all other neurons but not to
itself. The weight of connection between two neurons is described as a
function of the contrast of gray-level values and the distance betwee
n the two pixels. The initial state of each neuron represents the norm
alized gray-level value of the corresponding pixel in the original ima
ge. As a result of Hopfield-network analysis, neuron states are modifi
ed till convergence. Even though the neuron states are analog, they ar
e close to 1.0 in all regions except edges, where the corresponding ne
urons have near-0.0 state values. A robust threshold on the output lev
el of the converged network can be easily set up at 0.5 to extract edg
es.