Chinese Wine Classification through Micrograph Using Combined Feature and Fuzzy Cluster

Micrographs of Chinese wines show floccule, stick and granule of variant shape and size. Different wines have variant microstructure and micrographs, we study the classification of Chinese wines based on the micrographs. In this work, ten Chinese wines are determined or classified in the system, such as Wuliangye, Luzhoulaojiao, Xushui, Jiannanchun, Maotai and et.al. For each wine, we collect micrographs of deferent resolution (300 nm times 300 nm, 1.5 mum times 1.5 mum and 5 mum times 5 mum). We compute the two sets of features: statistical measure (energy, mean and variance) of images filtered by multi-scale and multi-orientation Gabor filters, and moment invariants in the steerable pyramid transform representation. The means of vectors generated from same resolution micrographs obtained from each wine are employed as the corresponding cluster center. We adopt the semi-unsupervised classification method improved FCM in which the cluster centers are given. We compare the recognition results for different choices of features.