Deep Learning Fabric Defect Detection Project (Manual Labelling/AI Training)
OtherImageBounding Box
Developed a system for detecting defects in fabric using deep learning techniques, involving manual labeling of fabric images as part of the training dataset. Responsible for annotating images to identify various types of fabric defects, ensuring high-quality ground truth data. Employed AI tools (YOLO v9e) and data augmentation strategies to enhance detection accuracy and model robustness.
• Labeled fabric images with bounding boxes to identify and classify defect types.
• Manually curated and validated annotation datasets for model training.
• Collaborated with team members to optimize annotation consistency.
• Utilized Python-based tools alongside YOLO v9e for labeling and dataset management.
Developed a system for detecting defects in fabric using deep learning techniques, involving manual labeling of fabric images as part of the training dataset. Responsible for annotating images to identify various types of fabric defects, ensuring high-quality ground truth data. Employed AI tools (YOLO v9e) and data augmentation strategies to enhance detection accuracy and model robustness. • Labeled fabric images with bounding boxes to identify and classify defect types. • Manually curated and validated annotation datasets for model training. • Collaborated with team members to optimize annotation consistency. • Utilized Python-based tools alongside YOLO v9e for labeling and dataset management.
2023 - 2024