Abstract: A signal processing system for a video camera uses a single neural network to implement multiple nonlinear signal processing functions. In one example, the neural network implements gamma correction, contrast compression, color correction, high pass filtering and aperture correction as a combined function which is emulated by the network. The network is trained off-line using back propagation to emulate the entire composite function for a set of parameters which results in multiple sets of weighting factors. Then, using the stored multiple sets of weighting factors as initial values, the neural network is "re-trained" on-line for each new parameter setting. The use of a single neural network in place of the multiple dedicated processing functions reduces engineering effort to develop the product and may reduce the cost of the total system.

Abstract: In one embodiment, the video signal generator outputs a standardized analog video signal. The signal generator includes a clock controlling a sequential address generator. The address generator activates a memory device that is, for example, a ROM. A distortion conditioned standardized digital video signal is stored in the ROM. This distortion conditioned signal has distortion correction characteristics matching an output filter. Following the ROM is a D to A converter that converts the conditioned digital video signal into a conditioned analog video signal. A simple filter follows the D to A converter. The filter introduces distortion into the signal applied at its input but since that signal already has distortion correction characteristics therein, the distortion correction characteristics of the input signal match and substantially cancel the distortion introduced into that signal by the filter. Therefore, a standardized analog video signal is produced at the output of the filter.