Intelligent animal fibre classification with artificial neural networks

The scale patterns of cashmere and fine wool are different and that is a major reference distinguishing them from each other. A technique commonly used consists of analysing their SEM image for detecting cuticle scale edge height ( CSH) of fibre. However, the method is expensive and has an average error of 8%. In this paper, a lower cost method is presented. The microscopic images of fibre captured by CCD camera are transformed into skeletonised binary images only having one pixel wide. Four shape parameters of fibre scale are measured and a LVQ neural network model including these measuring data is developed to classify the two type fibres. The simulation testing results show that whether on training set or testing set, the model can always distinguish cashmere from fine wool (70s) effectively and the average classification accuracy are higher than 93%.