A Novel Texture Sensor for Fabric Texture Measurement and Classification

Abstract

Surface texture is one of the important cues for human beings to identify different fabrics. This paper presents a novel design of a surface texture sensor by imitating human active texture perception by touch. A thin polyvinylidene fluoride (PVDF) film is used as the sensitive element to fabricate a high-accuracy, high-speed-response fabric surface texture sensor, and a mechanism is designed to produce the relative motion at a certain speed between the texture sensor and the surface of the perceived fabric with constant contact force. Thus, the surface texture property can be measured as the output charge of the PVDF film of the sensor induced by the small height/depth variation of the moving fabric surface. A texture feature extraction method by compressing the zero value spectral lines in frequency domain is proposed. In addition, a radial basis function (RBF) neural networks based on unsupervised K-means clustering algorithm is used as classifier for texture recognition. The experiments show that the proposed texture sensor is effective in detecting the feature signals of fabric surface textures, which are suitable for the RBF networks to classify the different fabrics.