Preventing Fake Accounts on Social Media Using Face Recognition Based on Convolutional Neural Network

Singh, Vernika; Shanmugam, Raju; Awasthi, Saatvik

doi:10.1007/978-981-15-8677-4_19

Cited by 9 publications

(1 citation statement)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, [5] employed CNNs for an Evoting system, combining face recognition with blockchain technology and blind signature mechanisms to enhance the security of online voting. Also, [6] tackled the problem of fake accounts on online social networks using CNNs; [7] used CNNs for patient identification in hospitals; [8] It is a type of neural network architecture known as a Siamese Network, that is designed to acquire the ability to discriminate between two distinct inputs. The model is trained directly using Euclidean distance, utilizing a dataset consisting of 8 million distinct identities and a total of 100-200 million photographs.…”

Section: Deep Learning Models For Facial Recognitionmentioning

confidence: 99%

LunchByte: A Facial Recognition-Based Payment System for Health-Conscious Elementary Student Meals

Mirza,

Bitar,

Alfahid

et al. 2024

TEM Journal

View full text Add to dashboard Cite

A significant number of elementary school students experience challenges related to lunch, including forgetting lunch money, lacking awareness of their individual dietary needs, and the importance of balanced nutritional choices for their overall health. Numerous parents and guardians struggle to monitor their children at school, control their purchasing behaviors, and maintain their health. Therefore, this research aims to enhance the efficiency and monitoring of elementary school students' lunch choices. LunchByte, a face recognition system developed in this study assists elementary in monitoring lunch expenses concerning their dietary restrictions. The main feature of LunchByte is using a student’s face print to generate a custom menu tailored to their allergies/diet restrictions and allowing them to pay with a prepaid balance added by their guardians. The evaluation of this system involves conducting model testing to assess the accuracy of facial recognition, integration testing to examine the interaction between different components of the system, and usability testing with end-users to evaluate the user experience. The results of these tests indicate that the system achieves high levels of accuracy and user satisfaction. The study is important because it has the potential to improve the overall health of young children.

show abstract

Section: Deep Learning Models For Facial Recognitionmentioning

confidence: 99%