Super-resolution (SR) technique reconstructs a higher-resolution image. For more than three decades SR has been developed, both multi-frame and single-frame SR have significant applications in our daily life.Finger print recognition system is used as an application of super resolution in forensic department. Latent ﬁngerprints have been used as an important evidence to identify criminals in law enforcement agencies for more than a century.Prior to feature extraction, ﬁngerprint enhancement is necessary to remove noises and enhance the clarity of ridge structures in latent ﬁngerprints. First, the total variation model is applied to decompose into cartoon and texture components. The cartoon component with most of the nonﬁngerprint patterns is removed as the structured noise, whereas the texture component consisting of the weak latent ﬁngerprint is enhanced in the next stage..A multiscale patch-based sparse representation method is used for the enhancement of the texture component. Gabor elementary functions use dictionaries to capture the characteristics of ﬁngerprint ridge structure, and multiscale patch-based sparse representation is iteratively applied to reconstruct high-quality ﬁngerprint image.