Kontrol Presentasi Berbasis Pose Tangan Menggunakan Convolutional Neural Network (CNN)

Rajwa, M. Dafa Raisya (2023) Kontrol Presentasi Berbasis Pose Tangan Menggunakan Convolutional Neural Network (CNN). Other thesis, Institut Teknologi Sepuluh Nopember.

Text 07211940000069-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 September 2025. Download (5MB) | Request a copy

Abstract

Dalam melakukan presentasi terdapat beberapa pilihan cara kontrol yang tersedia saat ini, salah satunya menggunakan keyboard. Namun, terdapat beberapa kekurangan dalam cara tersebut yaitu kontrol presentasi harus menekan tombol pada laptop secara langsung, sehingga tidak bisa dikendalikan dari jarak jauh dan dirasa kurang interaktif. Dalam penelitian ini, kontrol presentasi dilakukan menggunakan pose tangan sehingga tidak memerlukan kontak langsung lagi dengan perangkat yang digunakan untuk presentasi. Metode yang diterapkan sendiri menggunakan salah satu metode machine learning dalam mengolah citra yaitu Convolutional Neural Network. Berdasarkan pelaksanaan tugas akhir ini didapatkan hasil bahwa model dapat mendeteksi pose tangan dan terhubung dengan beberapa fungsi kontrol dalam aplikasi presentasi Microsoft PowerPoint menggunakan metode Convolutional Neural Network dengan tingkat akurasi tertinggi sebesar 99.00% pada jarak sekitar 40 cm dan kondisi cahaya minimal 40 lx
===================================================================================================================================
When presenting, there are several control options currently available, one of which is using keyboard. However, there are several drawbacks in this method, namely the presentation control must press the buttons on the laptop directly, so it cannot be controlled remotely and feels less interactive. In this study, presentation control was carried out using hand poses so that it did not require direct contact with the device used for presentation. The implementation method uses one of the machine learning methods in processing images, namely Convolutional Neural Network. Based on the implementation of this final project, the results show that the model can detect hand poses and is connected to several control functions in the Microsoft PowerPoint presentation application using the Convolutional Neural Network method with an accuracy rate of 99% in ideal conditions. The ideal conditions are at a distance of about 40 cm, light conditions around 40 lx, and using the author’s hand in the test

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Pose Tangan, Presentasi, Convolutional Neural Network; Hand Pose, Presentation, Convolutional Neural Network
Subjects:	Q Science > Q Science (General) > Q325.5 Machine learning. Q Science > QA Mathematics > QA76.87 Neural networks (Computer Science) T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK5105.546 Computer algorithms
Divisions:	Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Computer Engineering > 90243-(S1) Undergraduate Thesis
Depositing User:	M. Dafa Raisya Rajwa
Date Deposited:	24 Aug 2023 01:15
Last Modified:	24 Aug 2023 01:15
URI:	http://repository.its.ac.id/id/eprint/100995

Actions (login required)

View Item