PERANCANGAN SISTEM DETEKSI BOTOL MENGGUNAKAN ESP32-CAM DAN METODE HAAR CASCADE BERBASIS PENGENALAN OBJEK

RIZKI, RETNO BANGUN (2023) PERANCANGAN SISTEM DETEKSI BOTOL MENGGUNAKAN ESP32-CAM DAN METODE HAAR CASCADE BERBASIS PENGENALAN OBJEK. S1 thesis, Universitas Mercu Buana Jakarta.

[img]
Preview
Text (COVER)
01 COVER.pdf

Download (329kB) | Preview
[img]
Preview
Text (ABSTRAK)
02 ABSTRAK.pdf

Download (24kB) | Preview
[img] Text (BAB I)
03 BAB 1.pdf
Restricted to Registered users only

Download (118kB)
[img] Text (BAB II)
04 BAB 2.pdf
Restricted to Registered users only

Download (517kB)
[img] Text (BAB III)
05 BAB 3.pdf
Restricted to Registered users only

Download (429kB)
[img] Text (BAB IV)
06 BAB 4.pdf
Restricted to Registered users only

Download (690kB)
[img] Text (BAB V)
07 BAB 5.pdf
Restricted to Registered users only

Download (24kB)
[img] Text (DAFTAR PUSTAKA)
08 DAFTAR PUSTAKA.pdf
Restricted to Registered users only

Download (104kB)

Abstract

This research develops and implements a bottle object detection system using the ESP32-Cam module and Haar Cascade method based on object recognition. The stages involve collecting diverse bottle image datasets to train the Haar Cascade model. The training process utilizes machine learning and Haar Cascade algorithm to identify bottle objects. After the training is completed, the Haar Cascade model is implemented on the ESP32-Cam device for applications in various industries, automation, and monitoring. Based on the results of the device design and the bottle detection system using ESP32-Cam with Haar Cascade method based on object recognition integrated with a conveyor machine, it has been successfully implemented. The simplicity of the system requires several components such as Infrared sensor, Buzzer, LED, relay, LM2596, 24 VDC power supply, and DC motor. These components are interconnected and integrated with each other, enabling the system to detect bottle objects effectively. Based on the device design and testing, the bottle detection system using ESP32-CAM with Haar Cascade method based on object recognition has been successfully implemented. In the prototype testing, both hardware and software components functioned properly. The ESP32 sensor can detect moving bottle objects on the conveyor within a detection time range of 16 to 22 seconds, with an average accuracy of about 75% for glass bottles and 80% for plastic bottles. When a bottle is detected, the conveyor will continue to operate, and if the object is not a bottle, the system will stop with a red LED and buzzing sound. With these results, it can be concluded that the bottle detection system has been effectively designed and implemented. Keywords: Bottle Object Detection, ESP32-Cam, Haar Cascade, Machine Learning Penelitian ini mengembangkan dan mengimplementasikan sistem deteksi objek botol menggunakan modul ESP32-Cam dan metode Haar Cascade berbasis pengenalan objek. Tahapannya mencakup pengumpulan dataset gambar botol yang beragam untuk melatih model Haar Cascade. Pada proses pelatihan model dilakukan dengan memanfaatkan machine learning dan algoritma Haar Cascade untuk mengidentifikasi objek botol. Setelah pelatihan selesai, model Haar Cascade diimplementasikan pada perangkat ESP32-Cam untuk aplikasi dalam berbagai industri, otomatisasi, dan pemantauan. Berdasarkan hasil perancangan alat dan sistem deteksi botol menggunakan ESP32-Cam dengan metode Haar Cascade berbasis pengenalan objek yang telah terintegasi dengan mesin konveyor telah berhasil diimplementasikan dengan baik. Sehingga kesederhanaan sistem ini dibutuhkannya beberapa komponen komponen seperti sensor Infrared, Buzzer, LED, relay, LM2596, Catu daya 24 vdc, dan motor dc. Komponen tersebut saling terhubung dan terintegrasi satu dengan yang lainya, sehingga sistem mampu mendeteksi objek botol dengan baik. Berdasarkan hasil perancangan alat dan pengujian pada alat, sistem deteksi botol menggunakan ESP32-CAM dengan metode Haar Cascade berbasis pengenalan objek berhasil diimplementasikan dengan baik. Pada pengujian purwarupa, perangkat keras dan perangkat lunak berfungsi dengan baik. Sensor ESP32 mampu mendeteksi objek botol berjalan di atas konveyor dengan waktu deteksi berkisar 16 hingga 22 detik, dengan akurasi rata-rata sekitar 75% untuk botol kaca dan 80% untuk botol berbahan plastik. Ketika botol terdeteksi, konveyor akan terus berjalan, dan jika objek bukan botol, sistem akan berhenti dan ditandai dengan lampu merah yang menyala dan buzzer berbunyi. Dengan hasil ini, dapat dikatakan bahwa sistem deteksi botol telah berhasil dirancang dan diimplementasikan secara efektif. Kata Kunci: Deteksi Objek Botol, ESP32-Cam, Haar Cascade, Machine Liearning.

Item Type: Thesis (S1)
Call Number CD: FT/ELK. 23 118
Call Number: ST/14/23/098
NIM/NIDN Creators: 41419110197
Uncontrolled Keywords: Deteksi Objek Botol, ESP32-Cam, Haar Cascade, Machine Liearning.
Subjects: 600 Technology/Teknologi > 620 Engineering and Applied Operations/Ilmu Teknik dan operasi Terapan
600 Technology/Teknologi > 620 Engineering and Applied Operations/Ilmu Teknik dan operasi Terapan > 621 Applied Physics/Fisika terapan > 621.3 Electrical Engineering, Lighting, Superconductivity, Magnetic Engineering, Applied Optics, Paraphotic Technology, Electronics Communications Engineering, Computers/Teknik Elektro, Pencahayaan, Superkonduktivitas, Teknik Magnetik, Optik Terapan, Tekn
Divisions: Fakultas Teknik > Teknik Elektro
Depositing User: Annas Tsabatulloh
Date Deposited: 20 Sep 2023 02:36
Last Modified: 20 Sep 2023 02:36
URI: http://repository.mercubuana.ac.id/id/eprint/80771

Actions (login required)

View Item View Item