hiiii i am sami i want the matlab code for the human ege estimation through fingerprint as soon as possible........
Posts: 14,118
Threads: 61
Joined: Oct 2014
Fingerprints are the most commonly used tests to identify individuals. In this paper we use human fingerprints as evidence to determine human age. Fingerprints are widely used to identify individuals, but the age estimate is an emerging field. Encouraged by the fact that the human fingerprint differs in width ranging from birth to middle age, but the patterns remain unchanged. The two 2D-Discrete Wavelet Transformation (DWT) and Principal Component Analysis (PCA) methods are used in combination to extract the characteristics of the fingerprint, vector support machines (SVM) are used as classifier. The fingerprint image obtained passes through two characteristic extraction process steps and results in separate feature vectors which are then combined to produce a final future vector. The SVM classifies the fingerprint image to a respected age class by comparing the final future vector with the fingerprints of the database. This method can be useful in criminal investigations to reduce the search space of suspects.
Humans have distinctive and unique traits that can be used to distinguish them thus, acting as a form of identification. Biometrics identifies individuals by measuring some aspect of an individual's anatomy or physiology, such as hand geometry or fingerprint, which consists of a pattern of intertwined crests and valleys. The 2015 elections in Nigeria were welcomed by some petitions, including underage voters. The need for a gender and age detector system is a major concern for organizations at all levels where the integrity of the information can not be compromised. This work developed a system that determines the range of human age and gender through the analysis of fingerprints trained with the Neural Net of Propagation Back (for the classification of gender) and PCT DWT + (for the classification by age). A total of 280 fingerprints were collected from people of different ages and genders. 140 of these samples were used to train the system database; 70 males and 70 females respectively. This was done for the age groups 1-10, 11-20, 21-30, 31-40, 41-50, 51-60 and 61-70 accordingly. In order to determine the gender of an individual, the person's Ridge Thickness Valley Thickness Ratio (RTVTR) was taken into consideration. The result showed a classification accuracy of 80.00% for women and 72.86% for men, while 115 subjects from 140 (82.14%) were correctly classified in age.