The echocardiogram is the technique which is used in the diagnosis of most of the heart related diseases. Echocardiogram contains less information hence the diagnosis of the disease from the Echocardiogram videos is time consuming task. It required more human efforts to make a decision. Hence the automatic approach to detect the cardiovascular diseases with minimum computing time and high accuracy is necessary. In this approach, the automatic dilated cardiomyopathy (DCM) and Atrial Septal Defect (ASD) disease detection using machine learning approach has been proposed. The database contains the ultrasound videos of ASD, DCM and normal cases. The features extracted from the image and the classified the extracted features using supervised support vector machine algorithm. The proposed system achieved the accuracy of 98.30%. © 2018 IEEE.