TY - JOUR

T1 - Towards universal haptic library

T2 - Library-based haptic texture assignment using image texture and perceptual space

AU - Hassan, Waseem

AU - Abdulali, Arsen

AU - Abdullah, Muhammad

AU - Ahn, Sang Chul

AU - Jeon, Seokhee

N1 - Funding Information: This work is supported by the NRF of Korea through the Global Frontier R&D Program (2012M3A6A3056074) and through the ERC program (2011-0030075), and by the MSIP through IITP (No.2017-0-00179, HD Haptic Technology for Hyper Reality Contents). Publisher Copyright: © 2008-2011 IEEE.

PY - 2018/4/1

Y1 - 2018/4/1

N2 - In this paper, we focused on building a universal haptic texture models library and automatic assignment of haptic texture models to any given surface from the library based on image features. It is shown that a relationship exists between perceived haptic texture and its image features, and this relationship is effectively used for automatic haptic texture model assignment. An image feature space and a perceptual haptic texture space are defined, and the correlation between the two spaces is found. A haptic texture library was built, using 84 real life textured surfaces, by training a multi-class support vector machine with radial basis function kernel. The perceptual space was classified into perceptually similar clusters using K-means. Haptic texture models were assigned to new surfaces in a two step process; classification into a perceptually similar group using the trained multi-class support vector machine, and finding a unique match from within the group using binarized statistical image features. The system was evaluated using 21 new real life texture surfaces and an accuracy of 71.4 percent was achieved in assigning haptic models to these surfaces.

AB - In this paper, we focused on building a universal haptic texture models library and automatic assignment of haptic texture models to any given surface from the library based on image features. It is shown that a relationship exists between perceived haptic texture and its image features, and this relationship is effectively used for automatic haptic texture model assignment. An image feature space and a perceptual haptic texture space are defined, and the correlation between the two spaces is found. A haptic texture library was built, using 84 real life textured surfaces, by training a multi-class support vector machine with radial basis function kernel. The perceptual space was classified into perceptually similar clusters using K-means. Haptic texture models were assigned to new surfaces in a two step process; classification into a perceptually similar group using the trained multi-class support vector machine, and finding a unique match from within the group using binarized statistical image features. The system was evaluated using 21 new real life texture surfaces and an accuracy of 71.4 percent was achieved in assigning haptic models to these surfaces.

KW - Image features

KW - Multi-dimensional scaling

KW - Perceptual space

KW - Psycho-physics

UR - http://www.scopus.com/inward/record.url?scp=85038861331&partnerID=8YFLogxK

U2 - 10.1109/TOH.2017.2782279

DO - 10.1109/TOH.2017.2782279

M3 - Journal article

C2 - 29911984

AN - SCOPUS:85038861331

VL - 11

SP - 291

EP - 303

JO - IEEE Transactions on Haptics

JF - IEEE Transactions on Haptics

SN - 1939-1412

IS - 2

ER -