A Digital Noise Reducer for Encoded NTSC Signals

Movie denoising by average of warped lines

Here, we present an efficient method for movie denoising that does not require any motion estimation. The method is based on the well-known fact that averaging several realizations of a random variable reduces the variance. For each pixel to be denoised, we look for close similar samples along the level surface passing through it. With these similar samples, we estimate the denoised pixel. The method to find close similar samples is done via warping lines in spatiotemporal neighborhoods. For that end, we present an algorithm based on a method for epipolar line matching in stereo pairs which has per-line complexity O (N), where N is the number of columns in the image. In this way, when applied to the image sequence, our algorithm is computationally efficient, having a complexity of the order of the total number of pixels. Furthermore, we show that the presented method is unsupervised and is adapted to denoise image sequences with an additive white noise while respecting the visual details on the movie frames. We have also experimented with other types of noise with satisfactory results.

The effect of temporal image filters on observer-dependent contrast metrics

Interframe correlation resulting from filtering diminishes eye integration signal-to-noise ratio (SNR) improvement. This reduces the SNR improvement used to predict improved minimum resolvable contrast or temperature difference to approximately half of that achieved at the monitor. Results are included for mean and recursive filters versus filter, delay, and blurring parameters.