Rendi Ardiansyah, - (2024) PERANCANGAN MODEL DETEKSI PLAT NOMOR MENGGUNAKAN YOLO-V8, PENGENALAN TEKS TESSERACT DAN KEAMANAN ENKRIPSI AES. S1 thesis, Universitas Pendidikan Indonesia.
Abstract
Penelitian ini berfokus pada perancangan dan pengembangan model deteksi objek menggunakan YOLO-v8, pengenalan teks menggunakan Tesseract, dan keamanan enkripsi menggunakan AES. Model yang dikembangkan bertujuan untuk merancang model deteksi plat nomor menggunakan YOLO-v8, pengenalan teks tesseract dan keamanan enkripsi AES. Metode penelitian yang digunakan adalah Design and Depelopment (D&D) dengan tahapan yang tersusun sistematis dan menghasilkan suatu produk yaitu model yang dikembangkan. Pengujian model deteksi YOLO-v8 mendapatkan hasil precision mencapai nilai 0,98; recall mencapai nilai 0,98; mAP50 mencapai nilai 0,99; dan mAP50-95 mencapai 0,78. Hasil ini menunjukan model dapat mendeteksi objek pada berbagai kondisi. Sedangkan dalam mengenali teks menggunakan Tesseract mencapai persentase 96% dengan jumlah karakter benar 373 dari 386 karakter. Pada enkripsi menggunakan Advanced Encryption Standar (AES) telah berhasil dilakukan untuk mengamankan data plat nomor. Selain itu, berhasil mengklasifikasi plat nomor menjadi ganjil atau genap berdasarkan karakter numerik terakhir. Penelitian ini menunjukan hasil yang baik dalam integrasi YOLO-v8, Tesseract, dan Advanced Encryption Standar (AES) pada model deteksi plat nomor, pengenalan teks, dan enkripsi pada sistem ganjil atau genap. ----------- using YOLO-v8, text recognition using Tesseract, and encryption security using AES. The developed model aims to design a license plate detection model using YOLO-v8, tesseract text recognition and AES encryption security. The research method used is Design and Depelopment (D&D) with stages that are systematically arranged and produce a product, namely the developed model. Testing the YOLO-v8 detection model results in precision reaching a value of 0.98; recall reaches a value of 0.98; mAP50 reaches a value of 0.99; and mAP50-95 reaches 0.78. These results show that the model can detect objects in various conditions. While in recognizing text using Tesseract, the percentage reached 96% with the number of correct characters 373 out of 386 characters. Encryption using Advanced Encryption Standard (AES) has been successfully performed to secure license plate data. In addition, it successfully classifies license plates into odd or even based on the last numeric character. This research shows good results in the integration of YOLO-v8, Tesseract, and Advanced Encryption Standard (AES) in the license plate detection model, text recognition, and encryption in odd or even systems.
![[img]](http://repository.upi.edu/style/images/fileicons/text.png) |
Text
S_TEKOM_2007064_Title.pdf Download (260kB) |
|
Text
S_TEKOM_2007064_Chapter1.pdf Download (408kB) |
|
Text
S_TEKOM_2007064_Chapter2.pdf Restricted to Staf Perpustakaan Download (439kB) |
|
Text
S_TEKOM_2007064_Chapter3.pdf Download (645kB) |
|
Text
S_TEKOM_2007064_Chapter4.pdf Restricted to Staf Perpustakaan Download (3MB) |
|
Text
S_TEKOM_2007064_Chapter5.pdf Download (515kB) |
|
Text
S_TEKOM_2007064_Appendix.pdf Restricted to Staf Perpustakaan Download (1MB) |
| Item Type: | Thesis (S1) |
|---|---|
| Additional Information: | https://scholar.google.com/citations?hl=en&user=Jsx0vlsAAAAJ&scilu=&scisig=ANI4uE0AAAAAZtaWw5UaQAdvEhaQZ4FBq0wUmI4&gmla=AC6lMd-PTfGdOyvtIuviDjfv8qEe0OgLJdGOwqg1XuP-U_N5LGK81FlsGr7TkgsH69Ix7xIpSYA-Vx5y6TGmtAzjvSzM10rhDweCMwA&sciund=8784794649887876164 ID SINTA Dosen Pembimbing: MUHAMMAD TAUFIK DWI PUTRA: 6745726 MUNAWIR: 6745899 |
| Uncontrolled Keywords: | sistem ganjil atau genap, You Only Look Once; Tesseract; Advanced Encryption Standard; odd or even system |
| Subjects: | L Education > L Education (General) T Technology > T Technology (General) |
| Divisions: | UPI Kampus cibiru > S1 Teknik Komputer |
| Depositing User: | Rendi Ardiansyah |
| Date Deposited: | 23 Sep 2024 02:27 |
| Last Modified: | 23 Sep 2024 02:27 |
| URI: | http://repository.upi.edu/id/eprint/122551 |
Actions (login required)
 |
View Item |