NOTICING THE MISSING CHILD USING MACHINE LEARNING WITH RESNET 50 AND VGG 16
Author(s):
Sai Greeshma Sree Pagidimarri, Velisala Madhu Babu, Komma Sanjay Bhargav, Gogula Vijay Kumar
Keywords:
Face recognition, missing child identification, deep learning, CNN, VGG-Face, and multi-class SVM.
Abstract
Consistently, countless youths are accounted for missing in India. In cases of missing children, a significant number of children remain unidentified. A clever deep learning strategy for recognizing a detailed missing child from accessible pictures of an enormous number of youngsters utilizing facial acknowledgment is portrayed in this work. A shared webpage can have landmarks, comments, and photos of questionable children added by the public. The image will be instantly compared to the repository's registered images of the missing child. The youngster's image is sorted, and the photograph from the data set of missing kids with the best match is picked. Using the public-provided face image, a deep learning model is prepared to precisely distinguish the missing child from the missing child picture information base. For face identification, the Convolutional Neural Network (CNN), a powerful deep learning method for picture-based applications, is utilized. Face descriptors are extracted from images using a pre-arranged CNN model VGG-Face significant plan. Our strategy, rather than different utilizations of deep learning, just utilizes a convolution network as an undeniable level component extractor, with a prepared SVM classifier taking care of youngster location. A deep learning model that is heartless toward commotion, enlightenment, contrast, impediment, picture posture, and youngster age is made by appropriately preparing the best face acknowledgment CNN model, VGG-Face. This model outperforms previous face recognition-based methods for identifying missing children. The kid identification system has a classification accuracy of 99.41%. 43 kids participated in the testing.
Article Details
Unique Paper ID: 158972

Publication Volume & Issue: Volume 9, Issue 11

Page(s): 229 - 236
Article Preview & Download


Share This Article

Conference Alert

NCSST-2023

AICTE Sponsored National Conference on Smart Systems and Technologies

Last Date: 25th November 2023

SWEC- Management

LATEST INNOVATION’S AND FUTURE TRENDS IN MANAGEMENT

Last Date: 7th November 2023

Latest Publication

Go To Issue



Call For Paper

Volume 10 Issue 1

Last Date for paper submitting for March Issue is 25 June 2023

About Us

IJIRT.org enables door in research by providing high quality research articles in open access market.

Send us any query related to your research on editor@ijirt.org

Social Media

Google Verified Reviews

Contact Details

Telephone:6351679790
Email: editor@ijirt.org
Website: ijirt.org

Policies

Important Links

Browse Rsearch papers