Our work was accepted for publication in Optimization and Engineering journal.

A user-centered side silhouette generation system for sedan cars based on shape templates.

Erkan Gunpinar, Salih Ertug Ovur, Serkan Gunpinar.
Optimization and Engineering, 1-41, 2018.

Abstract
A tool for the generation of side silhouettes for sedan cars is developed in this work; this enables ordinary people to produce personalized silhouettes that they prefer. Multiple silhouettes are collected from different car brands and analyzed in an off-line step. The silhouette is partitioned into nine characteristic lines, each of which is represented by either quadratic or cubic Bezier curves. Furthermore, geometric properties, such as geometric constraints and lower/upper bounds for the characteristic line dimensions, are determined. Next, a characteristic line is sampled via a spatial simulated annealing approach, while minimizing the Audze-Eglais potential energy between the sampled characteristic lines generated. These samples are called line templates or shape templates. A car side silhouette is encoded by a sequence of parameters, such as characteristic line lengths and heights and line template indices (i.e., 21 parameters in total). Once the values for these parameters are set, the silhouette can be generated. A user interface is provided for users to develop personalized car side silhouettes. According to the user study performed in this work, the developed tool enables users to obtain more desired/preferred silhouette(s) compared to those obtained using an interactive genetic algorithm.