Hassan, Waseem Abdulali, Arsen Abdullah, Muhammad Ahn, Sang Chul Jeon, Seokhee 2024-01-19T23:03:16Z 2024-01-19T23:03:16Z 2021-09-03 2018-04 1939-1412 https://pubs.kist.re.kr/handle/201004/121561 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. English IEEE COMPUTER SOC DIMENSIONS INFORMATION FEATURES MODELS Towards Universal Haptic Library: Library-Based Haptic Texture Assignment Using Image Texture and Perceptual Space Article 10.1109/TOH.2017.2782279 1 IEEE TRANSACTIONS ON HAPTICS, v.11, no.2, pp.291 - 303 IEEE TRANSACTIONS ON HAPTICS 11 2 291 303 scie scopus 000435560000013 2-s2.0-85038861331 Computer Science, Cybernetics Computer Science Article DIMENSIONS INFORMATION FEATURES MODELS Perceptual space multi-dimensional scaling image features psycho-physics