Automatic identification of special effects is a prerequisite for video indexing and intelligent video encoding. In this paper we present an algorithm for fade and dissolve scene change detection in video sequences. We use statistical features of the images to identify these special effects in uncompressed video. DC-estimation [4] is used to evaluate statistical features both in H.263 [lo] and MPEG-2 [1I] compressed video. Results show that these special effects can be identified accurately with the proposed scheme.