In the first part of this paper, a statistical analysis of the noise in the image, as a result of the insertion of the watermark by Liu and Tan algorithm, was performed. After that, using the base of test image the noise model was created. Based on the model, an algorithm for estimating the statistical parameters of noise, LTWM algorithm, (μ and σ
2) in the image with a watermark, was created. In the second part of this paper there is a description of the experiment in which a comparative analysis of the accuracy of estimating statistical parameters by the proposed LTWM algorithm and Algorithms from [3], [6] - [8], was performed. Algorithms have been applied on watermarked images from the NRCS base. The results of MAE and MSE between true and estimated variance are shown in tables and diagrams. In addition, the execution time of the tested algorithms was measured. A detailed comparative analysis has shown that the proposed LTWM algorithm was more precise, and has a shorter execution time, compared to the analysed algorithms.