Superellipse fitting to partial data

✍ Scribed by Xiaoming Zhang; Paul L. Rosin

• Book ID: 104161624
• Publisher: Elsevier Science
• Year: 2003
• Tongue: English
• Weight: 343 KB
• Volume: 36
• Category: Article
• ISSN: 0031-3203
• DOI: 10.1016/s0031-3203(02)00088-2

✦ Synopsis

Superellipses can be used to represent in a compact form a large variety of shapes, and are useful for modelling in the ÿelds of computer graphics and computer vision. However, ÿtting them to data is di cult and computationally expensive. Moreover, when only partial data is available the parameter estimates become unreliable. This paper attempts to improve the process of ÿtting to partial data by combining gradient and curvature information with the standard algebraic distance. Tests show that the addition of gradient information seems to enhance the robustness of ÿt and decrease the number of iterations needed. Curvature information appears to have only marginal e ects.