Micro calcifications in mammograms can be very hard to detect because of the different shapes of these tumors and because of the confusion with the background texture. Different wavelet filters' abilities are investigated to detect micro calcifications in mammogram-digitized images obtained from a Malaysian women sample. The images are obtained from a major hospital with positive micro calcifications in them identified by two separate radiologists. The wavelets' abilities to decompose the images into different sub bands localized both in frequency and time domains is utilized decomposing a set of mammogram images into different frequency sub bands and then reconstructing the images with the high frequency components, which correspond to details in the images (micro calcifications) and removing the low frequency components that correspond to the smooth background of the mammogram. Finally evaluation is done on the separate filters by consultations with the radiologists to confirm the results of detections.