Shoe prints at the place of crime provide valuable forensic evidence. In this paper, a novel approach of Shoeprint identification has been proposed and discussed. Fisher linear discrimination (FLD) is used to extract the features in shoe print images. For dimensionality reduction, PCA has been used. In addition to that, a pass band DCT has been used for dimensionality reduction prior to the extraction of feature vectors. This makes the shoe print recognition process more robust against degradations like noises, orientations buy laser pointer and blurred images which are common in shoe print images. It can significantly improve the recognition rates and effectively reduce the dimension of feature space.