Chinese aged liquor classification system using image combinational features

Abstract

The classification of Chinese aged liquor has always been a difficult problem in liquor-making industry in China. “Aged liquor” is the quality mark and business policy-making of enterprises to reap economic benefit.Chinese aged liquor can be classification or graded by the micrographs. Micrographs of Chinese aged liquor show floccules, stick and granule of variant shape and size. Different aged liquor have variant microstructure and micrographs, we study the classification of Chinese aged liquor based on the micrographs. Shape and structure of age liquor's particles in microstructure is the most important feature for recognition and classification. So we introduce a feature extraction method which can describe the structure and region shape of micrograph efficiently. First, the micrographs are enhanced using total variation denoise method, and segmented using relative entropy threshold method. Then features are extracted using proposed method in the paper based on area, perimeter and traditional shape feature. Eight kind's total 26 features are selected. Finally, Chinese aged liquor classification system based on micrograph using combination of shape and structure features and Back-Propagation neural network have been presented. We compare the recognition results for different choices of features (traditional shape features or proposed features). Such method is preferred for the classification of age liquor and it has the advantages including rapid and precise measurement, The experimental results show that the better classification rate have been achieved using the combinational features proposed in this paper.