Abstract
Face sketch recognition is a system that is used by law enforcement in crime investigation to track the identity of the suspect. The old approach is where a face sketch of a suspect is posted around the city in order to have someone recognize the identity of the suspect and report to the authorities. This approach had resulted in slow investigations and may give a chance for the suspect to escape before being apprehended. Information provided by the victim may also not be accurate enough and may get multiple suggestions of identity by different witnesses. So, with the help of this system. a sketched image of a suspect will be easily recognized based on the mugshot. Fast and accurate results given by deep learning based face sketch recognition can solve the problem of the old approach and lowering the chances of mis accusing somebody as the criminal. To test this system, a functionality test and a performance test were conducted. Results showed that the developed deep learning based face sketch recognition system had a very high accuracy.
Metadata
Item Type: | Book Section |
---|---|
Creators: | Creators Email / ID Num. Izahar Shah, Faiz Elmie Shah UNSPECIFIED Hashim, Muhamad Arif UNSPECIFIED |
Subjects: | Q Science > QA Mathematics > Instruments and machines > Electronic Computers. Computer Science > Neural networks (Computer science) |
Divisions: | Universiti Teknologi MARA, Perlis > Arau Campus > Faculty of Computer and Mathematical Sciences |
Page Range: | pp. 249-250 |
Keywords: | deep learning, face sketch, confusion matrix |
Date: | 2023 |
URI: | https://ir.uitm.edu.my/id/eprint/100693 |