A Study of Automatic Recognition of Three Rodent Species: Applying Mathematic Morphological Characters of Skull

Based on the digital image processing technology, this study applied the mathematic morphological character extracting software to get exterior shape feature from skull of three rodent species (Meriones unguiculatus, Microtus brandti and Rattus norvegicus). Via SPSS 13.0 for Windows, the data was explored for automatic recognition. 22 mathematic morphological characters were extracted and the results of univariate two-factor analysis of variance showed that all the features can provide a reliable foundation for a rapid automatic recognition, though failed to distinguish gender. Stepwise discriminatory method was applied and 9 parameters were selected for rodent identification: short axis(X1), perimeter(X2), eccentricity(X3), sphericity(X4), bump area(X5), paraxial area of enclosing rectangle(X6), hu1(X7), hu2(X8), hu3(X9). With the selected parameters, two standardized canonical discriminant functions were found: Y1 = 8.014X1 - 3.585X2 + 9.682X3 - 2.504X4 + 7.823X5 - 10.948X6 - 0.896X7 + 12.471X8 - 0.781X9; Y2 = 2.593X1 + 0.242X2 + 6.323X3 + 0.509X4 - 1.219X5 - 2.898X6 - 4.226X7 + 7.674X8 + 0.785X9. These two discriminant functions worked well for identification, the accuracy rate was 100%.