Akses terbuka Jurnal SINTA 1
Wire bonding object detection through deep learning architecture of oriented bounding boxes with YOLOv8
Bulletin of Electrical Engineering and Informatics · Vol. 15 No. 5 (2026) · hlm. 4202–4211
- ISSN
- 2089-3191, 2302-9285
- Terbit
- 2026-10-01
- Penerbit
- Institute of Advanced Engineering and Science (IAES)
- Bahasa
- en
Abstrak
Wire bonding inspection is a critical process in semiconductor packaging to ensure product quality and reliability. This study compares you only look once version 5 (YOLOv5) axis-aligned bounding box (AABB) and YOLOv8 oriented bounding box (OBB) for wire bond defect detection. The dataset comprises 1,063 images with 14,778 annotated bonding instances in both AABB and OBB formats. Experimental results are evaluated using precision, recall, F1-score, mAP@0.5, mAP@0.5:0.95, and inference time. The findings show that YOLOv8 OBB achieved superior recall (0.9904) and mAP@0.5:0.95 (0.6787) compared to YOLOv5 AABB, demonstrating improved localization of rotated and dense wire bonds. Customized YOLOv8 variants with feature pyramid network (FPN)+efficient multi-scale attention (EMCA) and spatial squeeze and excitation (SpatialSE)+EMCA were also tested, with FPN+EMCA achieving the best balance of accuracy and robustness. This work highlights the potential of OBB-based object detection in semiconductor manufacturing and establishes a foundation for future real-time inspection systems.
Kata kunci
Jaringan kolaborasi para penulis
31 penulis · 105 tautan kepenulisan bersama · 42 lintas organisasi
Arahkan kursor atau ketuk sebuah nama untuk menyorot rekan penulisnya. Klik dua kali untuk membuka halaman penulis.
- Universiti Teknikal Malaysia Melaka
- Universiti Teknologi Petronas
- Politeknik Muadzam Shah
- Universiti Tenaga Nasional
- University of Technology Malaysia
- National University of Malaysia
- Diponegoro University
- Organisasi lain
- Afiliasi tidak diketahui
- Organisasi berbeda
- Organisasi sama
- Afiliasi tidak diketahui
- Garis lebih tebal = lebih banyak artikel bersama · lingkaran lebih besar = lebih banyak artikel
Tampilkan sebagai tabel
| Rekan penulis | Organisasi | Artikel bersama |
|---|---|---|
| Lizawati Binti Salahuddin | Universiti Teknikal Malaysia Melaka | 4 |
| Sabrina Ahmad | Universiti Teknikal Malaysia Melaka | 3 |
| Chiah Chin Lim | Universiti Teknikal Malaysia Melaka | 3 |
| Raja Rina Raja Ikram | Universiti Teknikal Malaysia Melaka | 2 |
| Fiza Abdul Rahim | Universiti Tenaga Nasional | 2 |
| Teo Hong Chun | Universiti Teknikal Malaysia Melaka | 1 |
| Ummi Raba’ah Hashim | Afiliasi tidak diketahui | 1 |
| Kasturi Kanchymalay | Universiti Teknikal Malaysia Melaka | 1 |
| Nik Nurdini Wolseley | Universiti Teknikal Malaysia Melaka | 1 |
| Burhanuddin Mohd Aboobaider | Universiti Teknikal Malaysia Melaka | 1 |
| Naga Sunil Kumar Gandikota | Universiti Teknologi Petronas | 1 |
| Jafreezal Jaafar | Universiti Teknologi Petronas | 1 |
| Zainuddin Z. | Universiti Teknologi Petronas | 1 |
| P. Akhir E. A. | Universiti Teknologi Petronas | 1 |
| Rafizah Ab Rahman | Politeknik Muadzam Shah | 1 |
| Nur Dalila Abdullah | Politeknik Muadzam Shah | 1 |
| Ummi Namirah Hashim | Universiti Teknikal Malaysia Melaka | 1 |
| Mohd Hariz Naim | Universiti Teknikal Malaysia Melaka | 1 |
| Fauziah Binti Kasmin | Universiti Teknikal Malaysia Melaka | 1 |
| Yogan Jaya Kumar | Universiti Teknikal Malaysia Melaka | 1 |
| Zulaikha Zulaikha | Diponegoro University | 1 |
| Aina Khairina Ahmad Khair | Universiti Teknikal Malaysia Melaka | 1 |
| Wan Mohd Yaakob Wan Bejuri | Universiti Teknikal Malaysia Melaka | 1 |
| Mohd Murtadha Mohamad | University of Technology Malaysia | 1 |
| Masne Kadar | National University of Malaysia | 1 |
| Hadrina Sh-Hussain | Open University Malaysia | 1 |
| Deasy Wahyuni | Afiliasi tidak diketahui | 1 |
Afiliasi berasal dari OpenAlex; metadata OAI-PMH jurnal tidak memuatnya. Penulis tanpa ID OpenAlex dicocokkan berdasarkan nama, sehingga dua orang bisa tergabung atau satu orang bisa terpisah.