The aim of this study was to evaluate the potential of image analysis measurements in combination with the official analytical method for the detection of constituents of animal origin in feedstuffs, in distinguishing between bovine and swine (bone containing) material. Authentic samples of controlled origin containing bovine or swine meat and bone meals were analysed by the microscopic method, in accordance with the official analytical method. Sediment fractions of each sample were observed with a compound microscope at X40. A total of 362 bone fragment lacunae images were recorded and processed through image analysis software, deriving 30 geometric variables for each lacuna. Results indicated that not only were most variables significantly (P<0.001) different between bovine and swine samples, but also that two thirds of the same variables were bigger in bovine than in swine. This information, however, does not seem to be so effective in practice since bovine and swine features and measurements overlapped. It can be concluded that the microscopic method even when combined with image analysis does not fit all the requirements for accurately identifying prohibited ingredients of animal origin. A combined approach with other methods is therefore recommended.