Design Framework for Facial Gender Recognition Using MCNN
Sangita Choudhary1, Manisha Agarwal2, Manisha Jailia3
1Sangita Choudhary, Research Scholar, Banasthali Vidyapith, Banasthali, Jaipur (Rajasthan), India.
2Dr. Manisha Agarwal, Associate professor, Banasthali Vidyapith, Banasthali , Jaipur (Rajasthan), India.
3Dr. Manisha Jailia, Associate professor, Banasthali Vidyapith, Banasthali , Jaipur (Rajasthan), India.
Manuscript received on 18 February 2019 | Revised Manuscript received on 27 February 2019 | Manuscript published on 28 February 2019 | PP: 209-213 | Volume-8 Issue-3, February 2019 | Retrieval Number: C5791028319/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Facial Gender Recognition that allows automatic identification of gender from facial images, plays an important role in various applications. Even though it’s a challenging task, it has gained immense popularity recently, especially with the development and popularity of social platforms and social media. The main aim of this paper is to use the proposed framework to classify the facial images based on their gender. The proposed framework uses a modified form deep convolution neural network (CNN), to obtain greater performance and accuracy. This frame can be used even for processing huge quantity of data. Hence by combining both modified deep convolution neural network and KNN-classifier we have created an application that can classify gender accurately. The rate of accuracy can be increased by increasing the number of layers and simultaneously training the images using back propagation. The parallel processing concept can be enhanced using this framework.
Keywords: Convolution Neural Network (CNN), Deep Convolutional Neural Network, Deep Learning.
Scope of the Article: Deep Learning