TY - THES A1 - Kancharana, Sunil T1 - Image based damage detection of milling tools N2 - Tool sharpness is critical in the production process because the tool’s health determines the quality and precision of the workpiece. If the tool is damaged but the damage magnitude is minor, it is preferable to regrind the tool rather than purchasing a new one. This step aids in lowering the company’s overall tool accounting costs. However, the complex helical shaped geometry of the tool along with the highly reflective optical properties on the surface makes the tool regrinding a challenging task. The existing state-of-the-art machines that perform regrinding for the optical critical milling tools have a number of drawbacks. First and foremost would be the time. Even with the latest technology, it takes around 15-20 minutes to process the entire tool for damage detection and the other major setback is the cost of the equipment. The current thesis provides a novel approach to detect the damages of the tools using tool images that are taken under a controlled experimental setup which is relatively cheaper and faster than the current state of art machines. A homogeneous illumination has been provided on the optical critical milling tools to obtain high-quality images. These images are later processed through classical image processing algorithms to determine the damaged regions of the tool. Different methods such as image segmentation method where masking is performed on the tool image using an automatic thresholding parameter. Due to innovative light source simplified methods such as mean subtraction where the image mean is subtracted from the original image to obtain the anomalies, contour-box scan method in which the tool edge contour is obtained and then the regions beside the tool edge are examined, the slope method where the tool edge slope is studied to determine the broken edges are implemented for damage detection and the challenges encountered by each method due the optical critical properties of the tool and the drawbacks for each method are outlined. Y1 - 2022 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-33653 CY - Ingolstadt ER -