Object-shape classification and reconstruction from tactile images using image gradient

Garima Singh; Anwesha Khasnobish; Arindam Jati; Saugat Bhattacharyya; Amit Konar; D. N. Tibarewala; R. Janarthanan

doi:10.1109/EAIT.2012.6407870

Object-shape classification and reconstruction from tactile images using image gradient

Garima Singh
, Anwesha Khasnobish
, Arindam Jati
, Saugat Bhattacharyya
, Amit Konar
, D. N. Tibarewala
, R. Janarthanan

Jadavpur University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

7 Citations (Scopus)

Abstract

A human explores the world around him through his sense to touch. Touch sensation enables us to understand shape, texture and hardness of an object/surface necessary for efficient exploration. Incorporating artificial haptic sensory systems in rehabilitative aids and in various other human computer interfaces enhances the dexterity. This paper presents a novel approach of shape reconstruction and classification from the tactile images by touching the surface of various real life objects. Here four objects (viz. a planar surface, object with one edge, a cuboid i.e. object with two edges and a cylindrical object) have been used for the shape recognition purpose. A new gradient based feature extraction technique has been used for the classification purpose. The reconstruction algorithm also uses image gradients to differentiate between a surface having continuous curvature and a surface having sharp edge. Prewitt masks are used for determining the gradients. A comparison between the performances of different classifiers has been drawn to prove the efficacy of the shape classification algorithm.

Original language	English
Title of host publication	Proceedings - 2012 3rd International Conference on Emerging Applications of Information Technology, EAIT 2012
Publisher	IEEE
Pages	93-96
Number of pages	4
ISBN (Print)	9781467318259
DOIs	https://doi.org/10.1109/EAIT.2012.6407870
Publication status	Published (in print/issue) - 11 Jan 2013
Event	2012 3rd International Conference on Emerging Applications of Information Technology, EAIT 2012 - Kolkata, India Duration: 30 Nov 2012 → 1 Dec 2012

Publication series

Name	Proceedings - 2012 3rd International Conference on Emerging Applications of Information Technology, EAIT 2012

Conference

Conference	2012 3rd International Conference on Emerging Applications of Information Technology, EAIT 2012
Country/Territory	India
City	Kolkata
Period	30/11/12 → 1/12/12

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

Feed Forward Neural Network (FFNN)
k-Nearest Neighbor (kNN)
Linear Discriminant Analysis (LDA)
linear support vector machine (LSVM)
reconstruction
Shape classification
Support Vector Machine with Gaussian Radial Basis Function kernel (SVM-RBF)
tactile image

Access to Document

10.1109/EAIT.2012.6407870

Cite this

Singh, G., Khasnobish, A., Jati, A., Bhattacharyya, S., Konar, A., Tibarewala, D. N., & Janarthanan, R. (2013). Object-shape classification and reconstruction from tactile images using image gradient. In Proceedings - 2012 3rd International Conference on Emerging Applications of Information Technology, EAIT 2012 (pp. 93-96). Article 6407870 (Proceedings - 2012 3rd International Conference on Emerging Applications of Information Technology, EAIT 2012). IEEE. https://doi.org/10.1109/EAIT.2012.6407870

Singh, Garima ; Khasnobish, Anwesha ; Jati, Arindam et al. / Object-shape classification and reconstruction from tactile images using image gradient. Proceedings - 2012 3rd International Conference on Emerging Applications of Information Technology, EAIT 2012. IEEE, 2013. pp. 93-96 (Proceedings - 2012 3rd International Conference on Emerging Applications of Information Technology, EAIT 2012).

@inproceedings{ef5d7f54931a40199b657c4d3d5608c8,

title = "Object-shape classification and reconstruction from tactile images using image gradient",

abstract = "A human explores the world around him through his sense to touch. Touch sensation enables us to understand shape, texture and hardness of an object/surface necessary for efficient exploration. Incorporating artificial haptic sensory systems in rehabilitative aids and in various other human computer interfaces enhances the dexterity. This paper presents a novel approach of shape reconstruction and classification from the tactile images by touching the surface of various real life objects. Here four objects (viz. a planar surface, object with one edge, a cuboid i.e. object with two edges and a cylindrical object) have been used for the shape recognition purpose. A new gradient based feature extraction technique has been used for the classification purpose. The reconstruction algorithm also uses image gradients to differentiate between a surface having continuous curvature and a surface having sharp edge. Prewitt masks are used for determining the gradients. A comparison between the performances of different classifiers has been drawn to prove the efficacy of the shape classification algorithm.",

keywords = "Feed Forward Neural Network (FFNN), k-Nearest Neighbor (kNN), Linear Discriminant Analysis (LDA), linear support vector machine (LSVM), reconstruction, Shape classification, Support Vector Machine with Gaussian Radial Basis Function kernel (SVM-RBF), tactile image",

author = "Garima Singh and Anwesha Khasnobish and Arindam Jati and Saugat Bhattacharyya and Amit Konar and Tibarewala, \{D. N.\} and R. Janarthanan",

year = "2013",

month = jan,

day = "11",

doi = "10.1109/EAIT.2012.6407870",

language = "English",

isbn = "9781467318259",

series = "Proceedings - 2012 3rd International Conference on Emerging Applications of Information Technology, EAIT 2012",

publisher = "IEEE",

pages = "93--96",

booktitle = "Proceedings - 2012 3rd International Conference on Emerging Applications of Information Technology, EAIT 2012",

address = "United States",

note = "2012 3rd International Conference on Emerging Applications of Information Technology, EAIT 2012 ; Conference date: 30-11-2012 Through 01-12-2012",

}

Singh, G, Khasnobish, A, Jati, A, Bhattacharyya, S, Konar, A, Tibarewala, DN & Janarthanan, R 2013, Object-shape classification and reconstruction from tactile images using image gradient. in Proceedings - 2012 3rd International Conference on Emerging Applications of Information Technology, EAIT 2012., 6407870, Proceedings - 2012 3rd International Conference on Emerging Applications of Information Technology, EAIT 2012, IEEE, pp. 93-96, 2012 3rd International Conference on Emerging Applications of Information Technology, EAIT 2012, Kolkata, India, 30/11/12. https://doi.org/10.1109/EAIT.2012.6407870

Object-shape classification and reconstruction from tactile images using image gradient. / Singh, Garima; Khasnobish, Anwesha; Jati, Arindam et al.
Proceedings - 2012 3rd International Conference on Emerging Applications of Information Technology, EAIT 2012. IEEE, 2013. p. 93-96 6407870 (Proceedings - 2012 3rd International Conference on Emerging Applications of Information Technology, EAIT 2012).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Object-shape classification and reconstruction from tactile images using image gradient

AU - Singh, Garima

AU - Khasnobish, Anwesha

AU - Jati, Arindam

AU - Bhattacharyya, Saugat

AU - Konar, Amit

AU - Tibarewala, D. N.

AU - Janarthanan, R.

PY - 2013/1/11

Y1 - 2013/1/11

N2 - A human explores the world around him through his sense to touch. Touch sensation enables us to understand shape, texture and hardness of an object/surface necessary for efficient exploration. Incorporating artificial haptic sensory systems in rehabilitative aids and in various other human computer interfaces enhances the dexterity. This paper presents a novel approach of shape reconstruction and classification from the tactile images by touching the surface of various real life objects. Here four objects (viz. a planar surface, object with one edge, a cuboid i.e. object with two edges and a cylindrical object) have been used for the shape recognition purpose. A new gradient based feature extraction technique has been used for the classification purpose. The reconstruction algorithm also uses image gradients to differentiate between a surface having continuous curvature and a surface having sharp edge. Prewitt masks are used for determining the gradients. A comparison between the performances of different classifiers has been drawn to prove the efficacy of the shape classification algorithm.

AB - A human explores the world around him through his sense to touch. Touch sensation enables us to understand shape, texture and hardness of an object/surface necessary for efficient exploration. Incorporating artificial haptic sensory systems in rehabilitative aids and in various other human computer interfaces enhances the dexterity. This paper presents a novel approach of shape reconstruction and classification from the tactile images by touching the surface of various real life objects. Here four objects (viz. a planar surface, object with one edge, a cuboid i.e. object with two edges and a cylindrical object) have been used for the shape recognition purpose. A new gradient based feature extraction technique has been used for the classification purpose. The reconstruction algorithm also uses image gradients to differentiate between a surface having continuous curvature and a surface having sharp edge. Prewitt masks are used for determining the gradients. A comparison between the performances of different classifiers has been drawn to prove the efficacy of the shape classification algorithm.

KW - Feed Forward Neural Network (FFNN)

KW - k-Nearest Neighbor (kNN)

KW - Linear Discriminant Analysis (LDA)

KW - linear support vector machine (LSVM)

KW - reconstruction

KW - Shape classification

KW - Support Vector Machine with Gaussian Radial Basis Function kernel (SVM-RBF)

KW - tactile image

UR - https://www.scopus.com/pages/publications/84873497049

U2 - 10.1109/EAIT.2012.6407870

DO - 10.1109/EAIT.2012.6407870

M3 - Conference contribution

AN - SCOPUS:84873497049

SN - 9781467318259

T3 - Proceedings - 2012 3rd International Conference on Emerging Applications of Information Technology, EAIT 2012

SP - 93

EP - 96

BT - Proceedings - 2012 3rd International Conference on Emerging Applications of Information Technology, EAIT 2012

PB - IEEE

T2 - 2012 3rd International Conference on Emerging Applications of Information Technology, EAIT 2012

Y2 - 30 November 2012 through 1 December 2012

ER -

Singh G, Khasnobish A, Jati A, Bhattacharyya S, Konar A, Tibarewala DN et al. Object-shape classification and reconstruction from tactile images using image gradient. In Proceedings - 2012 3rd International Conference on Emerging Applications of Information Technology, EAIT 2012. IEEE. 2013. p. 93-96. 6407870. (Proceedings - 2012 3rd International Conference on Emerging Applications of Information Technology, EAIT 2012). doi: 10.1109/EAIT.2012.6407870

Object-shape classification and reconstruction from tactile images using image gradient

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this