Bilal, MühenadMühenadBilalPodishetti, RanadheerRanadheerPodishettiKoval, LeonidLeonidKovalGaafar, Mahmoud AbdelazizMahmoud AbdelazizGaafarGrossmann, DanielDanielGrossmannBregulla, MarkusMarkusBregulla2024-08-132024-08-132024-07-23Sensors 24 (15): 4777 (2024)https://hdl.handle.net/11420/48737In this work, we investigate the impact of annotation quality and domain expertise on the performance of Convolutional Neural Networks (CNNs) for semantic segmentation of wear on titanium nitride (TiN) and titanium carbonitride (TiCN) coated end mills. Using an innovative measurement system and customized CNN architecture, we found that domain expertise significantly affects model performance. Annotator 1 achieved maximum mIoU scores of 0.8153 for abnormal wear and 0.7120 for normal wear on TiN datasets, whereas Annotator 3 with the lowest expertise achieved significantly lower scores. Sensitivity to annotation inconsistencies and model hyperparameters were examined, revealing that models for TiCN datasets showed a higher coefficient of variation (CV) of 16.32% compared to 8.6% for TiN due to the subtle wear characteristics, highlighting the need for optimized annotation policies and high-quality images to improve wear segmentation.en1424-8220202415Multidisciplinary Digital Publishing Institutehttps://creativecommons.org/licenses/by/4.0/annotation protocolsannotation qualitydomain expertiseimage annotationIoU metricslabeling qualityneural network performancesemantic segmentationU-Net modelwear detection| machining toolsTechnology::621: Applied PhysicsComputer Science, Information and General Works::006: Special computer methods::006.3: Artificial IntelligenceTechnology::620: Engineering::620.1: Engineering Mechanics and Materials Science::620.11: Engineering MaterialsTechnology::621: Applied Physics::621.3: Electrical Engineering, Electronic Engineering::621.38: Electronics, Communications EngineeringJournal Article2024-08-0910.15480/882.1321210.3390/s2415477710.15480/882.13212Journal Article