Academic article

Identification of fat, protein matrix, and water/starch on microscopy images of sausages by a principal component analysis-based segmentation scheme

Kohler, Achim; Høst, Vibeke; Enersen, Grethe; Ofstad, Ragni

Publication details

Journal: Scanning, vol. 25, p. 109–115, 2003

Publisher: John Wiley & Sons

International Standard Numbers:
Printed: 0161-0457
Electronic: 1932-8745

Open Access: gold


A color-based segmentation scheme applied to microscopy images of cryosectioned 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. 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.