Applications of Neural Networks in Video Signal Processing

Part of Advances in Neural Information Processing Systems 3 (NIPS 1990)

Bibtex Metadata Paper


John Pearson, Clay D. Spence, Ronald Sverdlove


Although color TV is an established technology, there are a number of longstanding problems for which neural networks may be suited. Impulse noise is such a problem, and a modular neural network approach is pre(cid:173) sented in this paper. The training and analysis was done on conventional computers, while real-time simulations were performed on a massively par(cid:173) allel computer called the Princeton Engine. The network approach was compared to a conventional alternative, a median filter. Real-time simula(cid:173) tions and quantitative analysis demonstrated the technical superiority of the neural system. Ongoing work is investigating the complexity and cost of implementing this system in hardware.



Neural networks are most often considered for application in emerging new tech(cid:173) nologies, such as speech recognition, machine vision, and robotics. The fundamental ideas behind these technologies are still being developed, and it will be some time before products containing neural networks are manufactured. As a result, research in these areas will not drive the development of inexpensive neural network hard(cid:173) ware which could serve as a catalyst for the field of neural networks in general.

In contrast, neural networks are rarely considered for application in mature tech(cid:173) nologies, such as consumer electronics. These technologies are based on established principles of information processing and communication, and they are used in mil(cid:173) lions of products per year. The embedding of neural networks within such mass-