PROJECT TITLE :
Bayesian Structure-Preserving Image Contrast Enhancement and its Simplification
During this paper, an economical Bayesian framework is proposed for image contrast enhancement. Primarily based on the image acquisition pipeline, we tend to model the image enhancement downside as a maximum a posteriori (MAP) estimation downside, where the posteriori likelihood is formulated based on the native data of the given image. In our framework, we tend to categorical the probability model as a native image structure preserving constraint, where the overall effect of the shutter speed and camera response perform is approximated as a linear transformation. On the opposite hand, we style the prior model primarily based on the observed image and some statistical property of natural pictures. With the proposed framework, we have a tendency to can effectively enhance the contrast of the image in an exceedingly natural-trying method, whereas with fewer artifacts at the identical time. Moreover, so as to apply the proposed MAP formulation to typical enhancement issues, like image editing, we tend to more convert the estimation method into an intensity mapping method, which will achieve comparable enhancement performance with a abundant lower computational complexity. Simulation results have demonstrated the feasibility of the proposed framework in providing versatile and effective distinction enhancement.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here