Scientific Publications with referee

Identification of fat, protein matrix and water/starch on microscopy images of sausages by a PCA based segmentation scheme.

 

Artikkelen presenterer en ny bildeanalysemetode. Det er en segmenteringsmetode som gjør det mulig å skille fett, vann og protein på mikroskopi bilder av pølser. Dette gir mulighet til å kvantifisere disse komponentene i mikroskopibilder. Metoden er generell og kan brukes på ulike bildetyper, også på multispektrale bilder. Metoden er basert på principal komponent analyse (PCA). Det lages PCA modeller for objekter som skal segmenteres. Modellene lages ved en manuell segmentering av et utvalg av bildepiksler med en software laget til dette formålet. Softwaren kan også brukes som et treningsverktøy for mikroskopister.

Facts

Year 2003
Abstract A color-based segmentation scheme applied to microscopy images of cryo-sectioned sausages is proposed. The segmentation scheme is capable of segmenting three different levels on the microscopy images: the fat particles, the protein matrix and water/starch. The method is based on principal component analysis (PCA). A user-friendly program was developed for the manual segmentation of a selection of image pixels by microscopists. Principal component models based on the manually classified pixels are then used to segment fat, protein matrix and starch/water on microscopy images. The program can also be used as a training tool for microscopists.
Reference Kohler, A., Enersen, G., Høst, V., Ofstad, R. 2003. Identification of fat, protein matrix and water/starch on microscopy images of sausages by a PCA based segmentation scheme. Scanning, Vol 25, pp 109-115.
Publisher Scanning,

Related persons

  • Achim Kohler

    Research Scientist

    Phone: +47 64970240

    Cellphone: +47 901 80 765

  • Grethe Enersen

    Laboratory Leader

    Phone: +47 64970200

  • Vibeke Høst

    Food Technologist

    Phone: +47 64970285

  • Ragni Ofstad

    Research Director, Raw materials and Process Optimisation

    Phone: +47 64970293

    Cellphone: +47 90 59 29 81