Mammogram images are majorly used for detecting the breast cancer. The level of positivity of breast cancer is detected afterexcluding the pectoral muscle from mammogram images. Hence, it is very signifi cant to identify and segment the pectoralmuscle from the mammographic images. In this work, a new multilevel thresholding, on the basis of electro-magnetismoptimization (EMO) technique, is proposed. The EMO works on the principle of attractive and repulsive forces among thecharges to develop the members of a population. Here, both Kapur’s and Otsu based cost functions are employed with EMOseparately. These standard functions are executed over the EMO operator till the best solution is achieved. Thus, optimalthreshold levels can be identifi ed for the considered mammographic image. The proposed methodology is applied on all thethree twenty-two mammogram images available in mammographic image analysis society dataset, and successful segmentationof the pectoral muscle is achieved for majority of the mammogram images. Hence, the proposed algorithm is found tobe robust for variations in the pectoral muscle.