Article Per Year (5 Year)
p-Index From 2019 - 2024
0.23
P-Index
This Author published in this journals
All Journal JAMBURA JOURNAL OF PROBABILITY AND STATISTICS
Rahmat Setiawan Usman
Universitas Negeri Gorontalo
Computer Science & IT Decision Sciences, Operations Research & Management Environmental Science Social Sciences

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Implementasi Deep Learning dalam Pengklasifikasian Wajah Menggunakan Library Tensorflow pada Algoritma Convolutional Neural Network (CNN) Rahmat Setiawan Usman; Isran K. Hasan; Dewi Rahmawaty Isa
Jambura Journal of Probability and Statistics Vol 4, No 2 (2023): Jambura Journal Of Probability and Statistics
Publisher : Department of Mathematics, Universitas Negeri Gorontalo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37905/jjps.v4i2.18264

Abstract

The convolutional neural network is a deep learning method that functions to recognize and classify objects in an image. An example of its application is a facial recognition system which consists of a detection and classification process. Facial recognition by computers can be influenced by many things such as lighting, expressions, and the amount of dataset provided. This study aims to find out how to implement CNN to identify faces using Tensorflow with the Python programming language. The number of datasets used is 120 data and 10 respondents in total with different lighting conditions and shooting angles. Apart from the dataset, this study also uses several different scenarios in the training process, namely the difference in the number of epochs and the difference in the number of learning rates. Based on the results of the discussion, two models were obtained. In the first model, the results obtained an accuracy of 100% in the training process and 65% in the testing process. In the second model, the results obtained are 100% accuracy in the training process and 75% in the testing process. performance of the model made in this study can be said to be optimal in recognizing objects in several lighting conditions and image angles.
Co-Authors Dewi Rahmawaty Isa Isran K. Hasan