{"status":"public","author":[{"last_name":"Sander","full_name":"Sander, Tom","first_name":"Tom"},{"id":"38240","first_name":"Sven","last_name":"Lange","full_name":"Lange, Sven"},{"full_name":"Hilleringmann, Ulrich","last_name":"Hilleringmann","first_name":"Ulrich"},{"full_name":"Geneiß, Volker","last_name":"Geneiß","first_name":"Volker"},{"first_name":"Christian","last_name":"Hedayat","full_name":"Hedayat, Christian"},{"last_name":"Kuhn","full_name":"Kuhn, Harald","first_name":"Harald"}],"conference":{"end_date":"2022-04-28","name":"2022 Smart Systems Integration (SSI)","start_date":"2022-04-27","location":"Grenoble, France"},"year":"2022","_id":"33510","type":"conference","date_created":"2022-10-04T11:35:55Z","publication":"2022 Smart Systems Integration (SSI)","keyword":["Machine Learning","CNN","Hashing","semi-supervised learning"],"place":"Grenoble, France","abstract":[{"text":"In the manufacture of real wood products, defects can quickly occur during the production process. To quickly sort out these defects, a system is needed that finds damage in the irregularly structured surfaces of the product. The difficulty in this task is that each surface is visually different and no standard defects can be defined. Thus, damage detection using correlation does not work, so this paper will test different machine learning methods. To evaluate different machine learning methods, a data set is needed. For this reason, the available samples were recorded manually using a static fixed camera. Subsequently, the images were divided into sub-images, which resulted in a relatively small data set. Next, a convolutional neural network (CNN) was constructed to classify the images. However, this approach did not lead to a generalized solution, so the dataset was hashed using the a- and pHash. These hash values were then trained with a fully supervised system that will later serve as a reference model, in the semi-supervised learning procedures. To improve the supervised model and not have to label every data point, semi-supervised learning methods are used in the following. For this purpose, the CEAL method (wrapper method) is considered in the first and then the Π-Model (intrinsically semi-supervised).","lang":"eng"}],"doi":"10.1109/ssi56489.2022.9901433","date_updated":"2022-10-04T11:37:39Z","publication_status":"published","language":[{"iso":"eng"}],"title":"Detection of Defects on Irregularly Structured Surfaces using Supervised and Semi-Supervised Learning Methods","project":[{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"}],"department":[{"_id":"59"},{"_id":"485"}],"user_id":"38240","citation":{"apa":"Sander, T., Lange, S., Hilleringmann, U., Geneiß, V., Hedayat, C., &#38; Kuhn, H. (2022). Detection of Defects on Irregularly Structured Surfaces using Supervised and Semi-Supervised Learning Methods. <i>2022 Smart Systems Integration (SSI)</i>. 2022 Smart Systems Integration (SSI), Grenoble, France. <a href=\"https://doi.org/10.1109/ssi56489.2022.9901433\">https://doi.org/10.1109/ssi56489.2022.9901433</a>","ieee":"T. Sander, S. Lange, U. Hilleringmann, V. Geneiß, C. Hedayat, and H. Kuhn, “Detection of Defects on Irregularly Structured Surfaces using Supervised and Semi-Supervised Learning Methods,” presented at the 2022 Smart Systems Integration (SSI), Grenoble, France, 2022, doi: <a href=\"https://doi.org/10.1109/ssi56489.2022.9901433\">10.1109/ssi56489.2022.9901433</a>.","mla":"Sander, Tom, et al. “Detection of Defects on Irregularly Structured Surfaces Using Supervised and Semi-Supervised Learning Methods.” <i>2022 Smart Systems Integration (SSI)</i>, IEEE, 2022, doi:<a href=\"https://doi.org/10.1109/ssi56489.2022.9901433\">10.1109/ssi56489.2022.9901433</a>.","ama":"Sander T, Lange S, Hilleringmann U, Geneiß V, Hedayat C, Kuhn H. Detection of Defects on Irregularly Structured Surfaces using Supervised and Semi-Supervised Learning Methods. In: <i>2022 Smart Systems Integration (SSI)</i>. IEEE; 2022. doi:<a href=\"https://doi.org/10.1109/ssi56489.2022.9901433\">10.1109/ssi56489.2022.9901433</a>","chicago":"Sander, Tom, Sven Lange, Ulrich Hilleringmann, Volker Geneiß, Christian Hedayat, and Harald Kuhn. “Detection of Defects on Irregularly Structured Surfaces Using Supervised and Semi-Supervised Learning Methods.” In <i>2022 Smart Systems Integration (SSI)</i>. Grenoble, France: IEEE, 2022. <a href=\"https://doi.org/10.1109/ssi56489.2022.9901433\">https://doi.org/10.1109/ssi56489.2022.9901433</a>.","bibtex":"@inproceedings{Sander_Lange_Hilleringmann_Geneiß_Hedayat_Kuhn_2022, place={Grenoble, France}, title={Detection of Defects on Irregularly Structured Surfaces using Supervised and Semi-Supervised Learning Methods}, DOI={<a href=\"https://doi.org/10.1109/ssi56489.2022.9901433\">10.1109/ssi56489.2022.9901433</a>}, booktitle={2022 Smart Systems Integration (SSI)}, publisher={IEEE}, author={Sander, Tom and Lange, Sven and Hilleringmann, Ulrich and Geneiß, Volker and Hedayat, Christian and Kuhn, Harald}, year={2022} }","short":"T. Sander, S. Lange, U. Hilleringmann, V. Geneiß, C. Hedayat, H. Kuhn, in: 2022 Smart Systems Integration (SSI), IEEE, Grenoble, France, 2022."},"publisher":"IEEE","main_file_link":[{"url":"https://ieeexplore.ieee.org/document/9901433"}]}