Melola Discovery

← Melola Discovery

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

DOI
10.11591/eei.v15i5.11059
ISSN
2089-3191, 2302-9285
Terbit
2026-10-01
Penerbit
Institute of Advanced Engineering and Science (IAES)
Bahasa
en
Lisensi
creativecommons.org/licenses/by-sa/4.0/

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 penulisOrganisasiArtikel bersama
Lizawati Binti SalahuddinUniversiti Teknikal Malaysia Melaka4
Sabrina AhmadUniversiti Teknikal Malaysia Melaka3
Chiah Chin LimUniversiti Teknikal Malaysia Melaka3
Raja Rina Raja IkramUniversiti Teknikal Malaysia Melaka2
Fiza Abdul RahimUniversiti Tenaga Nasional2
Teo Hong ChunUniversiti Teknikal Malaysia Melaka1
Ummi Raba’ah HashimAfiliasi tidak diketahui1
Kasturi KanchymalayUniversiti Teknikal Malaysia Melaka1
Nik Nurdini WolseleyUniversiti Teknikal Malaysia Melaka1
Burhanuddin Mohd AboobaiderUniversiti Teknikal Malaysia Melaka1
Naga Sunil Kumar GandikotaUniversiti Teknologi Petronas1
Jafreezal JaafarUniversiti Teknologi Petronas1
Zainuddin Z.Universiti Teknologi Petronas1
P. Akhir E. A.Universiti Teknologi Petronas1
Rafizah Ab RahmanPoliteknik Muadzam Shah1
Nur Dalila AbdullahPoliteknik Muadzam Shah1
Ummi Namirah HashimUniversiti Teknikal Malaysia Melaka1
Mohd Hariz NaimUniversiti Teknikal Malaysia Melaka1
Fauziah Binti KasminUniversiti Teknikal Malaysia Melaka1
Yogan Jaya KumarUniversiti Teknikal Malaysia Melaka1
Zulaikha ZulaikhaDiponegoro University1
Aina Khairina Ahmad KhairUniversiti Teknikal Malaysia Melaka1
Wan Mohd Yaakob Wan BejuriUniversiti Teknikal Malaysia Melaka1
Mohd Murtadha MohamadUniversity of Technology Malaysia1
Masne KadarNational University of Malaysia1
Hadrina Sh-HussainOpen University Malaysia1
Deasy WahyuniAfiliasi tidak diketahui1

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.

Sumber metadata: OpenAlex API (jurnal SINTA, ADR 0048) https://openalex.org/S2765016208, pertama di-harvest 19 Nov 2026, terakhir terlihat 19 Nov 2026.
Metadata asli (oai_dc)
<oai_dc:dc xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/"><dc:title xml:lang="en">Wire bonding object detection through deep learning architecture of oriented bounding boxes with YOLOv8</dc:title><dc:creator>Yuen Chin Wong</dc:creator><dc:creator>Ngo Hea Choon</dc:creator><dc:creator>Ummi Rabaah Hashim</dc:creator><dc:creator>Mohd Hilmi Hasan</dc:creator><dc:subject>oriented bounding boxes</dc:subject><dc:subject>YOLOv8</dc:subject><dc:subject>YOLOv5</dc:subject><dc:subject>axis-aligned bounding boxes</dc:subject><dc:subject>semiconductor packaging</dc:subject><dc:subject>object detection</dc:subject><dc:subject>feature pyramid network</dc:subject><dc:subject>efficient multi-scale attention</dc:subject><dc:subject>real-time inspection</dc:subject><dc:description xml:lang="en">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.</dc:description><dc:publisher>Institute of Advanced Engineering and Science (IAES)</dc:publisher><dc:date>2026-10-01</dc:date><dc:type>info:eu-repo/semantics/article</dc:type><dc:format>application/pdf</dc:format><dc:identifier>https://doi.org/10.11591/eei.v15i5.11059</dc:identifier><dc:identifier>10.11591/eei.v15i5.11059</dc:identifier><dc:source>Bulletin of Electrical Engineering and Informatics; Vol 15 No 5 (2026); 4202-4211</dc:source><dc:source>2089-3191</dc:source><dc:source>2302-9285</dc:source><dc:language>en</dc:language><dc:relation>https://beei.org/index.php/EEI/article/download/11059/4998</dc:relation><dc:rights>https://creativecommons.org/licenses/by-sa/4.0/</dc:rights></oai_dc:dc>