Identification of Biometrics based on a Classical Mathematical Methods in Forensic Medicine Hamoodi Yahya Abdul Fattah1,*, Ramadhan Shatha Abdullah M.2 1Department of Mathematics, University of Mosul, Mosul, Iraq 2Dept. of Software Engineering, College of Computer Sc. & Math. University of Mosul Mosul, Iraq *Corresponding author: Yahya Abdul Fattah Hamoodi. Department of Mathematics, University of Mosul, Mosul, Iraq, E-mail: yahya.abdulfattah@uomosul.edu.iq
Online published on 17 July, 2019. Abstract Biometrics is one of the branches of artificial intelligence as well as one of the most important criteria used to identify and categorize people's identity. It has extensive uses and branches and important, and recently introduced the techniques of intelligence in the forensic medicine, which took all aspects of forensic medicine, for example medical examination and causes leading to death, as well as the identification of bodies is one of the important sections and effective role in forensic medicine. One of the most commonly used identification methods is facial recognition. Biometrics were carried out through a series of sequential steps. On the basis of which the database was extracted, and the preliminary treatment was done on the images based on the Kapoor sports candidate. The most important features were also extracted. The working stages included two methods: First, the traditional mathematical method using linear (KLT) and nonlinear (KPCA) method. Second: the smart method, using the algorithm (CS), the results were the best ever. With the highest acceptance rate reaching (98.25%). Data training and testing were carried out through the implementation of the (MATLAB-2015) program because of its flexibility and speed of implementation. Top Keywords Biometrics, Feature Extraction, Gabor Filter, Kernel Technology, Karhunen-Lo`eve Transformation, Kernel Principle Component Analysis, Cuckoo Algorithm. Top |