The particle filter is an effective image denoising technique. An important issue with the application of the particle filter is the selection of the filter parameters, which affect the results significantly. There are two main contributions of this paper. The first contribution is an estimation of the noise level. The second contribution is an improved particle filter (Rao-Blackwellized Particle Filter). The particle filter is combined with Kalman filter to form a new image denoising framework. The distribution of the discrete states is computed by using PF and the distribution of the continuous states are computed by using a bank of Kalman filters. An accurate proposal distribution is computed by using conditionally Gaussian state space models and Rao-Blackwellized particle filtering. This improved filter is very effective in eliminating noise in real noisy images. Experimental results carried out with real noisy digital mobile camera images and RBPF is compared with particle filter. In terms of noise removal RBPF outperforms for degraded mobile camera images.