Rancang Bangun Aplikasi Face Tracking dan Filter Berdasarkan Raut Wajah Menggunakan Algoritma Fisher-Yates Berbasis iOS

Ghani, Malik Abdul and Rusli, Andre and Iswari, Ni Made Satvika (2019) Rancang Bangun Aplikasi Face Tracking dan Filter Berdasarkan Raut Wajah Menggunakan Algoritma Fisher-Yates Berbasis iOS. Ultima Computing: Jurnal Sistem Komputer, 11 (1). ISSN 2549-4007

Full text not available from this repository.

Abstract

Expressions of facial expressions in addition to providing important emotional indicators, are very important objects in our daily lives too. Real-time video processing on mobile devices is a hot topic and has a very broad application. Photos that have used the filter have 21% more possibilities to be seen and 45% more likely to be commented on by photo consumers. The use of the Fisher-Yates algorithm is used as a filter scrambler for each facial expression emotion. The application is made for the iOS operating system with the Swift programming language that utilizes the Core ML and Vision framework. Custom Vision is used as a tool for creating and training models. In making a model, this study uses a dataset from Cohn-Kanade AU-Coded Facial Expression Database and Karolinska Directed Emotional Faces. Custom Vision can provide performance result training and provide precision and recall values ​​for data that has been trained. The facial expression match with the model is determined by the confidence level value. The results of trials with Hedonic Motivation System Adoption Model method produce a percentage of pleasure in using the application (joy) of 79.39% of the users agree that the application provides joy.

Item Type: Article
Subjects: 000 Computer Science, Information and General Works > 000 Computer Science, Knowledge and Systems > 005 Computer Programming
Divisions: Faculty of Engineering & Informatics > Informatics
Depositing User: Administrator UMN Library
Date Deposited: 13 Oct 2021 07:55
Last Modified: 13 Oct 2021 07:55
URI: https://kc.umn.ac.id/id/eprint/18730

Actions (login required)

View Item View Item