Tactile features: recognising touch sensations with a novel and inexpensive tactile sensor

Tadeo Corradi, Peter Hall, Pejman Iravani

Research output: Chapter in Book/Report/Conference proceedingChapter

1 Citation (Scopus)

Abstract

A simple and cost effective new tactile sensor is presented, based on a camera capturing images of the shading of a deformable rubber membrane. In Computer Vision, the issue of information encoding and classification is well studied. In this paper we explore different ways of encoding tactile images, including: Hu moments, Zernike Moments, Principal Component Analysis (PCA), Zernike PCA, and vectorized scaling. These encodings are tested by performing tactile shape recognition using a number of supervised approaches (Nearest Neighbor, Artificial Neural Networks, Support Vector Machines, Naive Bayes). In conclusion: the most effective way of representing tactile information is achieved by combining Zernike Moments and PCA, and the most accurate classifier is Nearest Neighbor, with which the system achieves a high degree (96.4%) of accuracy at recognising seven basic shapes.
LanguageEnglish
Title of host publicationAdvances in Autonomous Robotics Systems
Subtitle of host publicationLecture Notes in Computer Science
EditorsM. Mistry, A. Leonardis, M. Witkowski, C. Melhuish
PublisherSpringer
Pages163-172
Number of pages10
ISBN (Print)9783319104003
DOIs
StatusPublished - 2014
EventProceedings of the 15th Annual Conference, TAROS, 2014 - Birmingham, UK United Kingdom
Duration: 1 Sep 20143 Sep 2014

Publication series

NameLecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics
Volume8717

Conference

ConferenceProceedings of the 15th Annual Conference, TAROS, 2014
CountryUK United Kingdom
CityBirmingham
Period1/09/143/09/14

Fingerprint

Principal component analysis
Sensors
Computer vision
Support vector machines
Rubber
Classifiers
Cameras
Neural networks
Membranes
Costs

Cite this

Corradi, T., Hall, P., & Iravani, P. (2014). Tactile features: recognising touch sensations with a novel and inexpensive tactile sensor. In M. Mistry, A. Leonardis, M. Witkowski, & C. Melhuish (Eds.), Advances in Autonomous Robotics Systems: Lecture Notes in Computer Science (pp. 163-172). (Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics; Vol. 8717). Springer. https://doi.org/10.1007/978-3-319-10401-0_15

Tactile features : recognising touch sensations with a novel and inexpensive tactile sensor. / Corradi, Tadeo; Hall, Peter; Iravani, Pejman.

Advances in Autonomous Robotics Systems: Lecture Notes in Computer Science. ed. / M. Mistry; A. Leonardis; M. Witkowski; C. Melhuish. Springer, 2014. p. 163-172 (Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics; Vol. 8717).

Research output: Chapter in Book/Report/Conference proceedingChapter

Corradi, T, Hall, P & Iravani, P 2014, Tactile features: recognising touch sensations with a novel and inexpensive tactile sensor. in M Mistry, A Leonardis, M Witkowski & C Melhuish (eds), Advances in Autonomous Robotics Systems: Lecture Notes in Computer Science. Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics, vol. 8717, Springer, pp. 163-172, Proceedings of the 15th Annual Conference, TAROS, 2014, Birmingham, UK United Kingdom, 1/09/14. https://doi.org/10.1007/978-3-319-10401-0_15
Corradi T, Hall P, Iravani P. Tactile features: recognising touch sensations with a novel and inexpensive tactile sensor. In Mistry M, Leonardis A, Witkowski M, Melhuish C, editors, Advances in Autonomous Robotics Systems: Lecture Notes in Computer Science. Springer. 2014. p. 163-172. (Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics). https://doi.org/10.1007/978-3-319-10401-0_15
Corradi, Tadeo ; Hall, Peter ; Iravani, Pejman. / Tactile features : recognising touch sensations with a novel and inexpensive tactile sensor. Advances in Autonomous Robotics Systems: Lecture Notes in Computer Science. editor / M. Mistry ; A. Leonardis ; M. Witkowski ; C. Melhuish. Springer, 2014. pp. 163-172 (Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics).
@inbook{151c6c1798294026a2db56c1f2488cb0,
title = "Tactile features: recognising touch sensations with a novel and inexpensive tactile sensor",
abstract = "A simple and cost effective new tactile sensor is presented, based on a camera capturing images of the shading of a deformable rubber membrane. In Computer Vision, the issue of information encoding and classification is well studied. In this paper we explore different ways of encoding tactile images, including: Hu moments, Zernike Moments, Principal Component Analysis (PCA), Zernike PCA, and vectorized scaling. These encodings are tested by performing tactile shape recognition using a number of supervised approaches (Nearest Neighbor, Artificial Neural Networks, Support Vector Machines, Naive Bayes). In conclusion: the most effective way of representing tactile information is achieved by combining Zernike Moments and PCA, and the most accurate classifier is Nearest Neighbor, with which the system achieves a high degree (96.4{\%}) of accuracy at recognising seven basic shapes.",
author = "Tadeo Corradi and Peter Hall and Pejman Iravani",
year = "2014",
doi = "10.1007/978-3-319-10401-0_15",
language = "English",
isbn = "9783319104003",
series = "Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics",
publisher = "Springer",
pages = "163--172",
editor = "M. Mistry and A. Leonardis and M. Witkowski and C. Melhuish",
booktitle = "Advances in Autonomous Robotics Systems",

}

TY - CHAP

T1 - Tactile features

T2 - recognising touch sensations with a novel and inexpensive tactile sensor

AU - Corradi, Tadeo

AU - Hall, Peter

AU - Iravani, Pejman

PY - 2014

Y1 - 2014

N2 - A simple and cost effective new tactile sensor is presented, based on a camera capturing images of the shading of a deformable rubber membrane. In Computer Vision, the issue of information encoding and classification is well studied. In this paper we explore different ways of encoding tactile images, including: Hu moments, Zernike Moments, Principal Component Analysis (PCA), Zernike PCA, and vectorized scaling. These encodings are tested by performing tactile shape recognition using a number of supervised approaches (Nearest Neighbor, Artificial Neural Networks, Support Vector Machines, Naive Bayes). In conclusion: the most effective way of representing tactile information is achieved by combining Zernike Moments and PCA, and the most accurate classifier is Nearest Neighbor, with which the system achieves a high degree (96.4%) of accuracy at recognising seven basic shapes.

AB - A simple and cost effective new tactile sensor is presented, based on a camera capturing images of the shading of a deformable rubber membrane. In Computer Vision, the issue of information encoding and classification is well studied. In this paper we explore different ways of encoding tactile images, including: Hu moments, Zernike Moments, Principal Component Analysis (PCA), Zernike PCA, and vectorized scaling. These encodings are tested by performing tactile shape recognition using a number of supervised approaches (Nearest Neighbor, Artificial Neural Networks, Support Vector Machines, Naive Bayes). In conclusion: the most effective way of representing tactile information is achieved by combining Zernike Moments and PCA, and the most accurate classifier is Nearest Neighbor, with which the system achieves a high degree (96.4%) of accuracy at recognising seven basic shapes.

UR - http://www.scopus.com/inward/record.url?scp=84906737738&partnerID=8YFLogxK

UR - http://dx.doi.org/10.1007/978-3-319-10401-0_15

U2 - 10.1007/978-3-319-10401-0_15

DO - 10.1007/978-3-319-10401-0_15

M3 - Chapter

SN - 9783319104003

T3 - Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics

SP - 163

EP - 172

BT - Advances in Autonomous Robotics Systems

A2 - Mistry, M.

A2 - Leonardis, A.

A2 - Witkowski, M.

A2 - Melhuish, C.

PB - Springer

ER -