English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The purpose of this paper is to design a solution to the problem of facialrecognition by use of convolutional neural networks, with the intention ofapplying the solution in a camera-based home-entry access control system. Morespecifically, the paper focuses on solving the supervised classificationproblem of taking images of people as input and classifying the person in theimage as one of the authors or not. Two approaches are proposed: (1) buildingand training a neural network called WoodNet from scratch and (2) leveragingtransfer learning by utilizing a network pre-trained on the ImageNet databaseand adapting it to this project's data and classes. In order to train themodels to recognize the authors, a dataset containing more than 150 000 imageshas been created, balanced over the authors and others. Image extraction fromvideos and image augmentation techniques were instrumental for datasetcreation. The results are two models classifying the individuals in the datasetwith high accuracy, achieving over 99% accuracy on held-out test data. Thepre-trained model fitted significantly faster than WoodNet, and seems togeneralize better. However, these results come with a few caveats. Because ofthe way the dataset was compiled, as well as the high accuracy, one has reasonto believe the models over-fitted to the data to some degree. An addedconsequence of the data compilation method is that the test dataset may not besufficiently different from the training data, limiting its ability to validategeneralization of the models. However, utilizing the models in a web-cam basedsystem, classifying faces in real-time, shows promising results and indicatesthat the models generalized fairly well for at least some of the classes (seethe accompanying video).

Application of Facial Recognition using Convolutional Neural Networks for Entry Access Control