Abstract
M. Ing. (Mechanical Engineering)
This research aims at identifying techniques which can be used to remove rain from a
digitized rain distorted image.
The research commenced with computer implemented rain removal techniques but also lead to camera obscuration techniques.
Camera rain obscuration technique: Before a rainy scene is digitized, rain can be removed from the projected image by the correct selection of camera aperture and
shutter speed settings. These settings will determine the way the real image is transformed through the lens and onto the recording plane.
Computer image restoration technique: Rain removal after digitization is performed
in both the frequency and the spatial domain by means of two dimensional image
processing and filtering techniques. Time consuming frequency domain techniques
were replaced by equivalent convolutional techniques.
Experiments on simulated and real scenes corrupted with rain indicated that it is
possible to improve the image appearance with only a marginal decrease in signal to
noise ratio.