This document describes a system for automated identification of individuals using forensic face sketches. The system uses discrete wavelet transform (DWT) to compress facial feature images from a database. It then uses a self-organizing map (SOM) neural network trained on the compressed images to classify input face sketches. The Matlab and Simulink tools are used to implement the system and simulate the neural network training. When an eyewitness provides a sketch, DWT compresses it and the SOM classifies it, potentially matching it to images in the database to identify suspects. If no match is found, the sketch is distributed to help law enforcement identify the individual from CCTV footage.