id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_4fmqd4q7pfb7nclr5zelrvwsja	Emmett Kerr	Material recognition using tactile sensing	2018	39	.pdf	application/pdf	11081	795	52	Distinguishing between objects and materials of different compressibility, temperature and texture can be achieved by performing complex manipulation tasks of the object by quickly identifying the physical nature of the material (e.g. metal, wood, plastic etc.) through completing a small number of initial We use an artificial fingertip to acquire data relating to the thermal properties and surface texture of materials, that are first analysed to initially its thermal properties may help to distinguish between very different materials which have similar compressibility, leading to improved classification assessed the ability of their sensors to classify between three different materials (denim, a photo and tape) based on their surface texture. with dimensionality-reduced mean values of filtered data, achieving a classification accuracy of material and object identification of over 97%. This approach utilises the multi-class SVM classification algorithm explained in Section 3.4.1 to firstly classify the materials into A hybrid approach of the SVM classifier for material group classification	./cache/work_4fmqd4q7pfb7nclr5zelrvwsja.pdf	./txt/work_4fmqd4q7pfb7nclr5zelrvwsja.txt