Skripsi

PENGENALAN WAJAH PADA PLATFORM EMBEDDED MELALUI IDENTIFIKASI MATA DAN HIDUNG MENGGUNAKAN METODE WEIGHTLESS NEURAL NETWORK.

---

Penilaian

---

Technological advances in the field of Computer Vision are increasingly complex, especially in research and industrial needs. Computer Vision allows computers to process and recognize images with a level of accuracy close to human capabilities. The purpose of this research is to develop a face recognition system that previously ran on a microcomputer, so that it can run on a microcontroller with limited memory. With this development, face recognition can be implemented in embedded systems. Weightless Neural Networks (WNN) is the method used in face recognition in this research. This method uses face data at a binary level and for binary recognition. Moreover, the sample face data in binary form is compared with the primary face data obtained from a particular camera or image. The dataset that will be created is 10 photos of the author's own face with a frame width of 110 x 110 to 90 x 90. Furthermore, each face photo will be processed by taking the eye and nose area and saving it into an image file. When the camera captures the image in real time, the Viola-Jones algorithm will perform preprocessing. When the face is detected, the size and position of the face frame will be calculated and the DC motor will move to adjust the face position of the frame. The face frame will be detected for both eyes and nose. Then, both images will be converted into binary format. Binary data will be sent from Raspberry Pi to Arduino Mega via serial to continue the recognition process. Of the 10 faces belonging to researchers who were tested, the decision resulted in 8 recognizable faces and 2 faces that failed to be recognized because the highest eye similarity was only worth 83.08% and 84.09%. Then of the 10 faces belonging to the researcher's friend tested the system produces a decision not to be recognized. because it only produces a similarity level for the eyes around 70% even though the results of the similarity level for the nose are around 85%

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2407000784	T139027	T1390272024	Central Library (Referens)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T1390272024

Publisher

Inderalaya : Prodi Sistem Komputer, Fakultas Ilmu Komputer Uniersitas Sriwijaya., 2024

Collation

xiv, 59 hlm.; Ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

006.307

Content Type

Text

Media Type

unmediated

Carrier Type

-

Edition

-

Subject(s)

Sistem Pakar
Prodi Sistem Komputer

Specific Detail Info

-

Statement of Responsibility

SEPTA

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment