In this interim study, we present the results of our approach when applied to a fairly small dataset. In future works, we will extend the dataset in order to include more classes and more patterns per class. In this work, we concentrated on SSIM in order to exploit the local structures in the 3D CAD models. SSIM was calculated directly at the image. However, only a small part of the image contains the relevant information. In a next step, we plan to use state-of-the-art computer vision models based on deep learning for feature extraction and dimensionality reduction. We expect that the computed features will be more representative and will help both improve accuracy and reduce computation and assessment times. Science & Research References: [1] Gunn, T. G. (1982). The mechanization of design and manufacturing. Scientific American, 247(3), 114-131. [2] Bai, J., Gao, S., Tang, W., Liu, Y., & Guo, S. (2010). Design reuse oriented partial retrieval of CAD models. Computer-Aided Design, 42(12), 1069- 1084. [3] Qin, F. W., Li, L. Y., Gao, S. M., Yang, X. L., & Chen, X. (2014). A deep learning approach to the classification of 3D CAD models. Journal of Zhejiang University SCIENCE C, 15(2), 91-106. [4] Wu, M. C., & Jen, S. R. (1996). A neural network approach to the classification of 3D prismatic parts. The International Journal of Advanced Manufacturing Technology, 11(5), 325-335. [5] Ip, C. Y., Regli, W. C., Sieger, L., & Shokoufandeh, A. (2003, June). Automated learning of model classifications. In Proceedings of the eighth ACM symposium on Solid modeling and applications (pp. 322-327). [6] Yiu Ip, C., & Regli, W. C. (2005). Content-based classification of CAD models with supervised learning. Computer-aided Design and Applications, 2(5), 609-617. [7] Ip, C. Y., & Regli, W. C. (2005, June). Manufacturing classification of CAD models using curvature and SVMs. In International Conference on Shape Modeling and Applications 2005 (SMI'05) (pp. 361-365). IEEE. [8] Barutcuoglu, Z., & DeCoro, C. (2006, June). Hierarchical shape classification using Bayesian aggregation. In IEEE International Conference on Shape Modeling and Applications 2006 (SMI'06) (pp. 44-44). IEEE. [9] Wei, W., Yang, Y., Lin, J., & Ruan, J. (2008, December). Color-based 3d model classification using hopfield neural network. In 2008 International Conference on Computer Science and Software Engineering (Vol. 1, pp. 883-886). IEEE. [10] Wang, W., Liu, X., & Liu, L. (2013). Shape matching and retrieval based on multiple feature descriptors. Computer Aided Drafting, Design and Manufacturing, 23(1), 60-67. [11] Chen, Q., Fang, B., Yu, Y. M., & Tang, Y. (2015). 3D CAD model retrieval based on the combination of features. Multimedia Tools and Applications, 74(13), 4907-4925. [12] Zheng, X. J., Wang, Y. S., Teng, H. F., & Qu, F. Z. (2009). Local scale-based 3D model retrieval for design reuse. The International Journal of Advanced Manufacturing Technology, 43(3-4), 294-303. [13] Renu, R., & Mocko, G. (2016). Retrieval of solid models based on assembly similarity. Computer-Aided Design and Applications, 13(5), 628-636. [14] Zhang, C., & Zhou, G. (2019). A view-based 3D CAD model reuse framework enabling product lifecycle reuse. Advances in Engineering Software, 127, 82-89. [15] Huang, B., Zhang, S., Huang, R., Li, X., & Zhang, Y. (2019). An effective retrieval approach of 3D CAD models for macro process reuse. The International Journal of Advanced Manufacturing Technology, 102(5-8), 1067-1089. [16] Kim, Sangpil and Chi, Hyung-gun and Hu, Xiao and Huang, Qixing and Ramani, Karthik (2020), A Large-scale Annotated Mechanical Components Benchmark for Classification and Retrieval Tasks with Deep Neural Net- works, Proceedings of 16th European Conference on Computer Vision (ECCV) [17] Gintautas Palubinskas (2017) Image similarity/distance measures: what is really behind MSE and SSIM?, International Journal of Image and Data Fusion, 8:1, 32-53, DOI: 10.1080/19479832.2016.1273259 Contact Contact Batin Latif Aylak +90 2163 333127 batin.latif@tau.edu.tr Thea Denell +49 30 006-214 thea.denell@ipk.fraunhofer.de 2021-2 ProductDataJournal 41