Shape modeling

Capturing the variability of fruit is useful in many ways, such as object detection and shape prediction. A statistical shape model is useful to predict the final size of a fruit, search for a correlation between stages of growth, or to estimate the volume of the fruit. Fruit package designers may use the shape model to evaluate the effect of the fruit on airflow characteristics and thus cooling uniformity.

The human body is a complex shape with many variations of which a thorough understanding is needed in order to design wearable products, like protective gear, head-sets, sports clothing, and orthotics, that are both functional and ergonomic. Current design approaches, relying only on 1D anthropometry and unrealistic, linearly scaled ISO-mannequins, require many prototyping and testing iterations. With the uprising of 3D scanning technology, however, an enormous amount of 3D data becomes available for the product developer.

The human body occurs in many shapes and sizes. For product developers it is important to have a realistic representation of the human body and the wide range of variations available, to be able to design ergonomic products with an optimal fit.

This toolkit contains a collection of algorithms, implemented in C++ and Python, used for statistical shape modeling and analysis of 3D surface populations:

• 3D surface parameterization algorithms for disc, sphere, and cylinder topology
• 3D surface alignment
• Parameterization-based MDL correspondence optimization for disc and cylinder topology
• elasticity and model regularized 3D surface registration
• GUI for surface annotation
• Statistical hypothesis testing for surface-based shape analysis

Designers of headgear often still have to rely on outdated anthropometric tables which offer only univariate measurements and very limited information about the variability of the human head. Promising solutions exist to supplement these tables with more complete 3D data, and several 3D model databases are currently on the market.

The clavicle is among the most frequently fractured bones in the human body and there is an increasing number of indications for surgical treatment of clavicular fractures. Due to the complex shape of the clavicle and its large variability, the design of osteosynthesis hardware is a very challenging task. Extensive knowledge of the anatomy of the clavicle clearly contributes to the improvement of such hardware.

Statistical Shape Models capture the shape variation of a training set of shapes and can be registered to an image of an object of the class they represent by simple adjustment of their parameters. We have applied statistical shape models of healthy tracheas to the assessment and stenting of tracheal stenosis. The idea is that a model with healthy tracheas only will not be influenced by local geometric variations typical of stenosis. The model produces a shape that is an estimation of the shape of the patient's trachea if it were not narrowed.