Automatic Fault Detection in Cheese using Computer Vision

In production of cheese with eyes (bubbles of CO2 often referred to as holes) there are occasionally problems with cracks in the cheese. These cracks can pose a problem when cutting up the cheese and they will, even though they are harmless, cause the cheese to appear less attractive for the consumer. Therefore the cheese producing industry is interested in the microbiological reasons behind the cracks. As one step to nd these statistics of when the cracks appear, what they look like and where on the cheese they are needs to be gathered. This master's thesis examines the possibility to use digital images taken when cutting up the cheese and automated image analysis to reach these statistics. This is done by taking a photo of the cut surface on all cheeses passing during the cutting-up process. The resulting images are then segmented by classifying the pixels as cheese or background according to their colour value and Bayes' Theorem. An ellipse is tted to the cheese pixels. Everything inside the ellipse is considered to be cut surface and everything outside background and is therefore removed. The image is recti ed to a top view. This allows the image to be taken with a bit tilted view. Several di erent lters, designed to be sensitive to cracks, are applied on the recti ed images. The output of these lters are used as features for the classi cation. The classi cation algorithm Support Vector Machine is then trained on training data consisting of three classes, at cheese, eyes and cracks. The resulting classi cation algorithm is used to classify all the pixels in the images into those three classes. The third interesting class, cracks, contains information about if there are any cracks and in that case how big, and where they are. The information can be specially treated with morphological operations to give a decision if the speci c cheese has a crack of a certain size. The results, from tests on images taken at a live industrial environment, are promising but future development is needed for the method to be usable commercially.