IJRE - International Journal of Research in Electronics ISSN: 2349-2511 SVM Classifier Based Automated whole Breast Ultrasound Screening V.SURESH BABU | R.SOUNDARRAJAN | M.VARATHARAJ 1 (Assistant professor, ECE PG department, Christ the King Engineering College, Coimbatore, India, sureshvece@gmail.com) 2 (PG department, Christ the King Engineering College, Coimbatore, INDIA, soundarrworld@gmail.com) 3 (Head of the Department of ECE, Christ the King Engineering College, Coimbatore, India, varatharaj_ms80@rediffmail.com) _____________________________________________________________________________________________ Abstract— This paper provides the derivation of speckle reducing anisotropic diffusion (SRAD), a diffusion method tailored to ultrasonic and radar imaging applications. SRAD is the edge-sensitive diffusion for speckled images, in the same way that conventional anisotropic diffusion is the edge-sensitive diffusion for images corrupted with a additive noise. The proposed method has been anisotropic diffusion Speckle detection. In resolution quality by means of using anisotropic diffusion Speckle detection. In the presence of speckle noise, speckle reducing anisotropic diffusion excels over the traditional speckle removal filters and over the conventional anisotropic diffusion method in terms of means preservation, variance reduction, and edge localization. Keywords— Anisotropic diffusion, image enhancement, speckle reduction, ultrasound imaging, Svm, watershed segmentation. ______________________________________________________________________________________________________________ 1. INTRODUCTION SPECKLE, a form of multiplicative, locally correlated noise, plagues imaging applications such as medical ultrasound image interpretation. For images that contain speckle, a goal of enhancement is to remove the speckle without destroying important image features. In certain applications, however, the removal of speckle may be counterproductive. We using watershed algorithm describes the specifics of the implementation and segmentation. We design the new multi-coordinate HOG (MCHOG) descriptors to accommodate the possible rotation. Support vector machine using to get normal or abnormal images. 2. ANISOTROPIC DIFFUSION VS ADAPTIVE SPECKLE FILTER. A. Anisotropic Diffusion The filter also strikes a balance between averaging and the all-pass filter. In this case, the balance is achieved by forming an exponentially shaped filter kernel that can vary from a basic average filter to an identity filter on a point wise, adaptive basis. Again, the response of the filter varies locally with the coefficient of variation. The Provide Frost filter also strikes a balance between averaging and the all- pass filter. In this case, the balance is achieved by forming an exponentially shaped filter kernel that can vary from a basic average filter. otherwise coefficient of variation, the filter is more average-like, and in cases of high coefficient of variation, the filter attempts to preserve sharp features by not averaging. When the coefficient of variation exists in between the two thresholds, a balance between averaging and the identity is computed (as with the standard Lee and Frost filters). B. system design. 3. WATERSHE ADLGORITHM. Over all watershed algorithm derives its name from the manner in which regions are segmented into catchment basins.The choice of height function depends on the application; the basic algorithm is independent of the height function. Therefore, the steps of the watershed segmentation algorithm are as follows: 1. Compute the curvature (or some other height function) at each vertex. 2. Find the local minima and assign each a unique label. 3. Find each flat area and classify it as a minimum or a plateau. 4. Loop through plateaus and allow each one to descend until a labeled region is encountered. IJRE - International Journal of Research in Electronics Volume: 01 Issue: 02 2014 www.researchscript.com 11