Analysis of Gender Prediction using Convolutional Neural Networks Algorithm compared over Scale-Invariant Feature Transform Algorithm

Analysis of Gender Prediction using Convolutional Neural Networks Algorithm compared over Scale-Invariant Feature Transform Algorithm

This study aims to find out and forecast the gender of the target audience. The planned research would base its predictions on features of the eyes, lips, chin, and nose. The research makes use of scalable feature transforms and new convolutional neural networks. Resources for Academic Work: With a...

Full description

Saved in:
Bibliographic Details
Published in:2024 15th International Conference on Computing Communication and Networking Technologies (ICCCNT) pp. 1 - 5
Main Authors: Jaivignesh, S., Sudha, I.
Format: Conference Proceeding
Language:English
Published: IEEE 24-06-2024
Subjects:
Accuracy
Classification algorithms
Convolutional neural networks
Gender Prediction
Image processing
Lips
Machine Learning
Machine learning algorithms
Nose
Novel Convolutional Neural Network
Prediction algorithms
Predictive models
Scale-Invariant Feature Transform
Statistical analysis
Surveillance Camera
Transforms
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This study aims to find out and forecast the gender of the target audience. The planned research would base its predictions on features of the eyes, lips, chin, and nose. The research makes use of scalable feature transforms and new convolutional neural networks. Resources for Academic Work: With a prior G-Power score of 80% and a confidence range of 95%, we can calculate the sample size. Two sets of twenty samples each indicate the new CNN and the SIFT Algorithm. Using the Python compiler, we conducted an experiment to see how much improvement in accuracy was achieved by both classifiers. See the outcomes down below. Even when presented with low-quality images that had issues with lighting and shading, the new Convolutional Neural Network classifier managed to beat the comparison model in terms of gender prediction. The results showed a statistical significance level of 0.001 (\mathbf{p}\lt0.05) and an accuracy of 93.48%. Statistical analysis reveals a striking discrepancy between the two sets of data. Finally, the findings show that the new CNN classifier is effective at detecting gender.
ISSN:2473-7674
DOI:10.1109/ICCCNT61001.2024.10724951