Scholarlink

This paper presents a tactile-sensing fingertip based on piezoelectric materials for texture classification. The system integrates a tactile sensing glove equipped with eight P(VDF-TrFE) sensors mounted on the index finger. A dataset comprising six naturalistic textures was collected to train a Convolution Recurrent Neural Network (C-RNN) classifier. The results demonstrate the effectiveness of the proposed approach, achieving a classification accuracy of 90.91%. This study highlights the potential of combining tactile sensing technologies with machine learning techniques for advanced texture recognition applications.

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

Convolution Recurrent Neural Network for Tactile Textural Classification

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Mohmad Yaacoub,
  • Razan Khalifeh,
  • Ali Ibrahim

摘要

This paper presents a tactile-sensing fingertip based on piezoelectric materials for texture classification. The system integrates a tactile sensing glove equipped with eight P(VDF-TrFE) sensors mounted on the index finger. A dataset comprising six naturalistic textures was collected to train a Convolution Recurrent Neural Network (C-RNN) classifier. The results demonstrate the effectiveness of the proposed approach, achieving a classification accuracy of 90.91%. This study highlights the potential of combining tactile sensing technologies with machine learning techniques for advanced texture recognition applications.