Machine vision is now being extensively used for defect detection in the manufacturing process of collagen-based products such as sausage skins which is a multi-million dollar industry worldwide. At present the industry standard uses a LabView software environment, whereby a graphical interface detects defects in the collagen skins. This method allows for false positives where creases or folds are resolved as defects instead of being by-products in the inspection process. This reduces system performance leading to resource wastage.
Charles Sturt University researchers developed a novel technique to enhance the current defect detection techniques that uses a function to probe colour deviation and fluctuation in collagen skins. Operationally, this method is more flexible and has increased accuracy than the original graphical LabView program. The new method has been incorporated into the existing programming environment of Debro Pty Ltd. After implementation of the new method, results demonstrate an average 26% increase in the ability to detect false positives with a corresponding substantial reduction in operating cost.