Application of wavelet based K-means algorithm in mammogram segmentation

Research in image processing has gained lots of momentum during past two decades. Now-a-days image processing techniques have found their way into computer vision, image compression, image security, medical imaging and more. This paper presents a research on mammography images using wavelet transformation and K - means clustering for cancer tumor mass segmentation. The first step is to perform image segmentation. It allows distinguishing masses and micro calcifications from background tissue. In this paper wavelet transformation and K- means clustering algorithm have been used for intensity based segmentation. The proposed algorithm is robust against noise. In this case, discrete wavelet transform (DWT) is used to extract high level details from MRI images. The processed image is added to the original image to get the sharpened image. Then K-means algorithm is applied to the sharpened image in which the tumor region can be located using the thresholding method. This paper validates the algorithm by detecting tumor region from an MRI image of mammogram. The combination of noise-robust nature of applied processes and the simple K-means algorithm gives better results.