Electrical component classification using 2D and 3D semantic segmentation

• Main Author: Zhou, Tongfang
• Other Authors: Jiang Xudong
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2022
• Subjects: Engineering::Electrical and electronic engineering
• Online Access: https://hdl.handle.net/10356/158187
• Institution: Nanyang Technological University

Description: The student will focus on 2D/3D semantic segmentation on various semiconductor component, such as TSV, logic bump, memory bump etc. The objective is to detect defects in the buried interconnects inside the chip by detecting and identifying the above structures. It involves 2D/3D data processing for deep learning algorithm in object detection and segmentation. The student is expected to take an active role in understanding and preprocessing the data and learning relevant deep learning networks. The student is also expected to implement 3D data augmentation and train the 3D semantic segmentation individually.