Authors :
B. Nagaraju; A. Venkata Reddy; T. Sri Manjunadha; M. Mohan Kumar
Volume/Issue :
Volume 8 - 2023, Issue 4 - April
Google Scholar :
https://bit.ly/3TmGbDi
Scribd :
https://bit.ly/3pcFvWi
DOI :
https://doi.org/10.5281/zenodo.7902020
Abstract :
The project titled “GENDER
CLASSIFICATION” predicts gender based on human
bodies or behavior. In this paper, we have worked on a
technique for classification of gender using python
algorithm. Human classification and identification have
been used for a very long period in many different fields.
areas such as government identification cards,
verification processes, etc. For the purpose of identifying
people, we have already created methods such as the
retinal scan, iris scan, fingerprint, and other complex
systems like DNA fingerprinting. Despite the fact that
these already developed methods are effective, the
hardware, software, and human competency
requirements are far too onerous for a number of
straightforward tasks that may or may not call for
professional efficiency. Technique reported in this paper
is simple and easy for gender classification which can be
performed using only a webcam and a decent computer
system. Automatic gender classification has become
relevant to an increasing number of applications,
particularly since the rise of social platforms and social
media. Even Nevertheless, compared to the enormous
performance improvements recently reported for the
closely related task of facial recognition, the
performance of present approaches on real-world
photographs still falls far short. In this paper, we
demonstrate that performance on these tasks can be
significantly improved by learning representations using
deep convolutional neural networks (CNN). In order to
do this, we suggest a straightforward convolutional net
architecture that may be applied even with a finite
supply of training data. We evaluate our method on the
recent Audience benchmark for gender estimation and
show it to dramatically outperform current state-of-theart methods.
Keywords :
Convolution Neural Networks, Machine Learning, Python, Support Vector Machine.
The project titled “GENDER
CLASSIFICATION” predicts gender based on human
bodies or behavior. In this paper, we have worked on a
technique for classification of gender using python
algorithm. Human classification and identification have
been used for a very long period in many different fields.
areas such as government identification cards,
verification processes, etc. For the purpose of identifying
people, we have already created methods such as the
retinal scan, iris scan, fingerprint, and other complex
systems like DNA fingerprinting. Despite the fact that
these already developed methods are effective, the
hardware, software, and human competency
requirements are far too onerous for a number of
straightforward tasks that may or may not call for
professional efficiency. Technique reported in this paper
is simple and easy for gender classification which can be
performed using only a webcam and a decent computer
system. Automatic gender classification has become
relevant to an increasing number of applications,
particularly since the rise of social platforms and social
media. Even Nevertheless, compared to the enormous
performance improvements recently reported for the
closely related task of facial recognition, the
performance of present approaches on real-world
photographs still falls far short. In this paper, we
demonstrate that performance on these tasks can be
significantly improved by learning representations using
deep convolutional neural networks (CNN). In order to
do this, we suggest a straightforward convolutional net
architecture that may be applied even with a finite
supply of training data. We evaluate our method on the
recent Audience benchmark for gender estimation and
show it to dramatically outperform current state-of-theart methods.
Keywords :
Convolution Neural Networks, Machine Learning, Python, Support Vector Machine.
