Automated Firearms Identification (AFI) systems assist to shed lights on criminal events by comparing evidences on cartridge cases and bullets and by matching similar ones that were fired from the same firearm. However, comparison process is difficult due to increased amount of incidents. Therefore, firearm brand detection is a useful step for the ballistic investigations to limit the comparison set and to increase the performance. In this paper, we propose global shape characteristics based classification for firearm brand detection. The proposed method makes use of autocorrelation function and power spectral density of the cartridge case area to extract the features related to global shape characteristics.