Every day over 100 Person will be diagnosed with a primary brain tumor and many more will be diagnosed with a cancer. Medical image processing is the most defy and invention field specially MRI imaging technique that scans and capture the internal structure of human brain. where specific type diagnoses of brain tumor can be a complicated affair, making confirmation of its diagnosis essential. In this paper, initially, brain images are filtered to remove unwanted particles, then a new method for automatic segmentation of lesion area is carried out based on mean and standard deviation. Combining both solidity property and morphological operation to detection only tumor from segmented image. Mathematical morphology such as close used to join narrow breaks regions in an object, fill the small holes and remove small objects. Employed wavelet transform to extract features from images, followed by applying principle component analysis (PCA) to reduce the dimensions of features. Extraction 13 feature of statistical and textural features to use them as input to the Artificial Neural Network (ANN) for classification. The algorithm is trained with 20 of brain MRI images and tested with 45 brain MRI images. Accuracy for this method was encourage and reach nearly 100% in identifying normal and abnormal tissues from brain MRI images. The proposed algorithm compared with other simila works and their results was better.