Noise removal and image enhancement
The captured either 2D or 3D data are usually unavoidably corrupted by imaging noise. Such noise corrupted data significantly affect its processing and interpretation. This project attempts to develop techniques to clean such data using such techniques as Markov random field and Split Bregman. An important constraint to impose is the coherence of properties where neighbouring pixels or points tend to have similar properties.
An image before (left) and after (right) noise removal