Treffer: Machine learning-based strategies for product quality monitoring.

Quality control is a vital aspect of manufacturing industries, whereby the final products are examined on a sample basis to identify any defects that may be present. Defect detection algorithms have demonstrated efficacy in identifying faults in several manufacturing products, including textiles, steel slabs, and glass items. Prompt and dependable inspection of components enables producers to detect potential faults early in the manufacturing process, resulting in decreased production time. In this project, open-source dataset images are being considered, which are analyzed through image processing and compared against quality standards. Defects are unwanted in many industries, and to remove such anomaly products, quality inspection departments are set up. The dataset used in this project contains images of a product captured from various angles to cover the entire product. A deep learning classification model has been developed, with the software written using Python and its libraries, primarily Keras and OpenCV libraries. The dataset comprises images of different defects classified by the type of defect, such as 'Pitted,' 'Scratches,' 'Rolled,' 'Patches,' 'Inclusion,' and 'Crazing.' The ultimate objective of this model is to identify the type of anomaly present in the image from the test dataset. [ABSTRACT FROM AUTHOR]

Copyright of AIP Conference Proceedings is the property of American Institute of Physics and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)