Scholarlink

This paper presents an application of deep learning techniques to the automatic detection of biometric features from digitized ear impressions. By leveraging deep neural network architectures—including state-of-the-art models such as YOLOv5 and YOLOv8—the proposed method efficiently identifies and localizes key anatomical markers of the human auricle. The system was evaluated under various configurations and data augmentation methods, which confirmed its effectiveness. This research highlights the potential of AI to streamline biometric analysis and support advanced forensic investigations.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Deep Learning for Automated Detection of Earprint Features

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Marcel Gańczarczyk,
  • Paweł Krzempek,
  • Nen Hirai,
  • Nobuyuki Nishiuchi,
  • Łukasz Więcław,
  • Łukasz Hamera

摘要

This paper presents an application of deep learning techniques to the automatic detection of biometric features from digitized ear impressions. By leveraging deep neural network architectures—including state-of-the-art models such as YOLOv5 and YOLOv8—the proposed method efficiently identifies and localizes key anatomical markers of the human auricle. The system was evaluated under various configurations and data augmentation methods, which confirmed its effectiveness. This research highlights the potential of AI to streamline biometric analysis and support advanced forensic investigations.