Ultrasonography is considered to be safest technique in medical imaging and hence is used extensively. Due to the presence of speckle noise and other constraints, establishing the general segmentation scheme for different classes of kidney in ultrasound image is a challenging task. This research aims at classification of medical ultrasound images of kidney as normal and abnormal kidney images In this work, the wiener filter is used to reduce the noise present in the image The gray-level co-occurrence matrix (GLCM) is used for examining the texture. It is used to find texture properties of an image by calculating the frequency of occurrence of pixel pairs with specific values and in a specified spatial relationship.