Hwang, T. J.Lee, K.Jeong, J. H.Oh, H. Y.Gershon Elber and Nicholas Patrikalakis and Pere Brunet2016-02-172016-02-1720043-905673-55-X1811-7783https://doi.org/10.2312/sm.20041402Custom-tailored products are defined as products having various sizes and shapes tailored to meet the customer's different tastes or needs. Thus fabrication of custom-tailored products inherently involves inefficiency. To minimize this inefficiency, a new paradigm is proposed in this work. In this paradigm, different parts are grouped into several groups according to their sizes and shapes. For grouping the different parts, similarity measurement algorithm is used. Similarity comparison starts with the determination of the closest pose between two shapes in consideration. The closest pose is derived by comparing the ray distances while one shape is virtually rotated with respect to the other. Shape similarity value and overall similarity value calculated from ray distances are also used for grouping. A prototype system based on the proposed methodology has been implemented and applied to the grouping and machining of the shoe lasts of various shapes and sizes.I.5.3 [Pattern Recognition] Similarity MeasuresH.3.3 [Information Search and Retrieval] Clustering10.2312/sm.20041402279-284