On Convergence of Hopfield Neural Networks for Real Time Image Matching

Provided by: International Journal on Emerging Technologies
Topic: Networking
Format: PDF
In this paper, the authors demonstrate on innovative approach for a fundamental problem in computer vision to map real time a pixel in one image to a pixel on another image of the same scene, which is generally called image correspondence problem. It is a novel real time image matching method which combines rotational invariant feature selection for real time images and optimization capabilities of hopfield neural networks. The most invariant image matching features are extracted from the reference image.

Find By Topic