Breast cancer is one of the most leading and common cause of cancer. It can be detected by infrared thermal imaging Technique by observing the temperature distribution on the breast. Breast thermography is considered as a valuable tool for early breast tumours detection. The fast growing tumour has a higher metabolic rate and associated increase in local vascularisation. It will cause the occurrence of some asymmetric heat patterns. Clinical interpretation of a breast thermogram can be done on the asymmetry analysis of the heat patterns visually and subjectively. In this paper, a new approach for early detection of breast cancer is proposed using asymmetry analysis of breast thermograms. The heat patterns are segmented and the asymmetry analysis is performed by using histogram generation and feature extraction. Extracted statical features clearly indicate the abnormality of a breast thermogram.