Image segmentation and bruise identification on potatoes using a Kohonen's self-organizing map

• Published in: Journal of food science Vol. 70; no. 7; pp. e415 - e417
• Main Authors: Marique, T, Pennincx, S, Kharoubi, A
• Format: Journal Article
• Language: English
• Published: Oxford, UK Blackwell Publishing Ltd 01.09.2005; Institute of Food Technologists; Wiley Subscription Services, Inc
• Subjects: appearance (quality); automatic detection; Biological and medical sciences; bruises; Food industries; Food preservation; food quality; Food science; Fruit and vegetable industries; Fundamental and applied biological sciences. Psychology; image analysis; Kohonen; neural networks; photography; postharvest injuries; potato; Potatoes; self-organizing map; bruises; Potato; Image analysis; Vegetables; Segmentation; Kohonen; Tuber; self-organizing map; Identification; Bruise
• ISSN: 0022-1147; 1750-3841
• DOI: 10.1111/j.1365-2621.2005.tb11469.x

Potato quality includes a low incidence of colored bruises resulting from bad storage or manipulation practices. We developed a procedure to process and segment potato images by using Kohonen's self-organizing map. Anomalous regions could be distinguished on 3 potato varieties. Bruises that were very dissimilar in appearance were correctly identified, and some particular defects such as green spots could be located as well.