Image Segmentation and 3D reconstruction for improved prediction of the sublimation rate during freeze drying
[EN] In a freeze drying process, the freezing step determines the pore size distribution within the product, which, in turn, affects the sublimation rate. Traditionally, pore analysis is carried out on SEM images by means of a manual, time-consuming approach. Here, an image segmentation technique wa...
| Autores: | , , , , |
|---|---|
| Tipo de recurso: | capítulo de libro |
| Fecha de publicación: | 2018 |
| País: | España |
| Institución: | Universitat Politècnica de València (UPV) |
| Repositorio: | RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia |
| Idioma: | inglés |
| OAI Identifier: | oai:riunet.upv.es:10251/117655 |
| Acceso en línea: | https://riunet.upv.es/handle/10251/117655 |
| Access Level: | acceso abierto |
| Palabra clave: | Drying Dehydration Dewatering Emerging technologies Products quality Process control Environmental Evaporation Sublimation Diffusion Energy Intensification Freezing Freeze-drying Image segmentation 3D reconstruction |
| Sumario: | [EN] In a freeze drying process, the freezing step determines the pore size distribution within the product, which, in turn, affects the sublimation rate. Traditionally, pore analysis is carried out on SEM images by means of a manual, time-consuming approach. Here, an image segmentation technique was used to automatize this process and improve its reliability. A 3D structure of the cake was then reconstructed from the distribution of the super-pixels. We show that the approach herein proposed can remarkably improve prediction of the sublimation rate with respect to traditional methods. |
|---|