PENGENALAN EKSPRESI WAJAH MANUSIA MENGGUNAKAN METODE CONVOLUTIONAL NEURAL NETWORK

PRATAMA, KURNIA SANDI and Mulya, Megah and Arsalan, Osvari (2020) PENGENALAN EKSPRESI WAJAH MANUSIA MENGGUNAKAN METODE CONVOLUTIONAL NEURAL NETWORK. Undergraduate thesis, Sriwijaya University.

	Text RAMA_55201_09021181320019.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (4MB) | Request a copy
	Text RAMA_55201_09021181320019_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (12MB) | Request a copy
Preview	Text RAMA_55201_09021181320019_ 0020026609_0028068806_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (4MB) | Preview
	Text RAMA_55201_09021181320019_ 0020026609_0028068806_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_55201_09021181320019_ 0020026609_0028068806_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_55201_09021181320019_ 0020026609_0028068806_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_55201_09021181320019_ 0020026609_0028068806_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (242kB) | Request a copy
	Text RAMA_55201_09021181320019_ 0020026609_0028068806_06.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (38kB) | Request a copy
	Text RAMA_55201_09021181320019_ 0020026609_0028068806_06 _ref.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (101kB) | Request a copy
	Text RAMA_55201_09021181320019_ 0020026609_0028068806_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (278kB) | Request a copy

Abstract

Human facial expressions recognition has been a challenge for researchers to facilitate a more friendly human-machine interface for multimedia products. However, recognition of human facial expressions is not an easy problem in machine learning methods. In this study the convolutional neural network method was used because in the study conducted by Alberto et al. (2016) and Pitaloka et al., (2017) show the performance of the convolutional neural network method is quite good in recognizing human facial expressions. In this study the convolutional neural network method is used to recognize 4 basic human facial expressions, which are happy, neutral, sad and surprised. Before the introduction, the input image is preprocessed, that is, the facial expression image is detected first by using the Viola Jones method which is used in taking facial areas. Furthermore, image binaryization is carried out which aims to produce an image of 0 or 1, so that the image is more easily processed and produces features of an image. Furthermore, the convolutional neural network method is used in the recognition process which consists of two stages, namely feedforward and backpropagation. Based on the evaluation conducted on the convolutional neural network method for recognition of human facial expressions using JAFFE dataset as many as 100 as a training dataset and 20 as a test dataset get an average accuracy of 90% which is calculated using confusion matrix. Based on these results it shows that the convolutional neural netwok method has good performance. Keyword : Facial expression recognition, Convolutional neural network, CNN, Viola jones,

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Facial expression recognition, Convolutional neural network, CNN, Viola jones
Subjects:	Q Science > Q Science (General) > Q334-342 Computer science. Artificial intelligence. Algorithms. Robotics. Automation.
Divisions:	09-Faculty of Computer Science > 55201-Informatics (S1)
Depositing User:	Users 7860 not found.
Date Deposited:	07 Sep 2020 03:43
Last Modified:	07 Sep 2020 03:43
URI:	http://repository.unsri.ac.id/id/eprint/34591

Actions (login required)

View Item