Image segmentation is an essential step in many advanced imaging applications, e.g., object tracking, pattern recognition, volume measurements, medical image analysis, and in the image guided procedures. Among the several types of images, magnetic resonance images (MRI), which represent the intensity variation of radio waves generated by biological systems when exposed to radio frequency pulses, have proved to be an effective imaging modality for imaging the inner tissues of the human. In this work, we have introduce new multiresolution algorithms for image segmentation that extend the well-known Expectation Maximization (EM) algorithm. The conventional EM algorithm has prevailed many other segmentation algorithms because of its simplicity and performance. However, it is found to be highly sensitive to noise. Multiresolution analysis has been used in order to take into account the effect of neighborhood pixels in the classification process to minimizes the sensitivity to noise. Different data sets were used to measure the performance of the proposed algorithms. The results show that the performance of the proposed algorithms has much increased over the conventional EM.