Authors :
Anitta George; Krishnendu K A; Anusree K; Adira Suresh Nair; Hari Shree
Volume/Issue :
Volume 5 - 2020, Issue 6 - June
Google Scholar :
http://bitly.ws/9nMw
Scribd :
https://bit.ly/2ClGISQ
DOI :
10.38124/IJISRT20JUN1116
Abstract :
Forensics and security at present often use
low technological resources. Security measures often fail
to update with the upcoming technology. This project is
based on implementing an automatic face recognition of
criminals or specific targets using machine-learning
approach. Given a set of features to a Generative
Adversarial Network(GAN), the algorithm generates an
image of the target with the specified feature set. The
input to the machine can either be a given set of features
or a set of portraits varying from frontals to side
profiles from which these features can be extracted. The
accuracy of the system is directly proportional to the
number of epochs trained in the network. The
generated output image can vary from primitive, low
resolution images to high quality images where features
are more recognizable. This is then compared with a
predefined database of existing people. Thus, the target
can immediately be recognized with the generation of
an artificial image with the given biometric feature set,
which will be again compared by a discriminator
network to check the true identity of the target.
Forensics and security at present often use
low technological resources. Security measures often fail
to update with the upcoming technology. This project is
based on implementing an automatic face recognition of
criminals or specific targets using machine-learning
approach. Given a set of features to a Generative
Adversarial Network(GAN), the algorithm generates an
image of the target with the specified feature set. The
input to the machine can either be a given set of features
or a set of portraits varying from frontals to side
profiles from which these features can be extracted. The
accuracy of the system is directly proportional to the
number of epochs trained in the network. The
generated output image can vary from primitive, low
resolution images to high quality images where features
are more recognizable. This is then compared with a
predefined database of existing people. Thus, the target
can immediately be recognized with the generation of
an artificial image with the given biometric feature set,
which will be again compared by a discriminator
network to check the true identity of the target.
