Literature review on CBR approches for matching composite sketches to facial photographs

Facial Sketches are most widely used in law enforcement agencies for identification and apprehension of suspect which may involve in several criminal activities. If the photographs of the suspect is store in the mug shot data base then the identity of the suspect is possible but in most of the cases that it is a possibility that the photographs of the suspect is not available in the mug shot then two methods are used first is forensic sketch and second is composite sketch software. The sketch used in investigations are either drawn by expert artist (forensic sketch) or created with the help of computer software (composite software sketches), the forensic sketch is drawn by expert artist by following the verbal description provided by an eyewitness. Previous research on sketch recognition in which the (LAP) i.e lightning aware preprocessing method, for face recognition was used as a preprocessing method. Another method was based on extended (ASM) i.e Active shape model for locating a facial feature and previous work for matching sketches to mug shot database was based on (LFDA) i.e local feature based discriminant analysis method was used. And also using PCA algorithm for matching hand drawn face sketch in forensic application. After that the (EUCLBP) i.e enhanced uniform circular local binary pattern for matching sketch in forensic application. But the above process are very slow for identifying the suspect so, for this purpose we propose a (CBR) i.e component based representation approach that is used for matching composite sketches to face photo and with the help of this method we can successfully recognize the face based on sketch.