Automatic diet management method and device based on image segmentation and stacking model

The invention relates to the technical field of image segmentation and deep learning, and discloses an automatic diet management method and device based on image segmentation and a stacking model. According to the method, an acquired food image is segmented based on a food image segmentation model,...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: NIE ZEDONG, LIU YUHANG, LI JINGZHEN, AO PENGFEI, HAN YUJIA
Format: Patent
Sprache:chi ; eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The invention relates to the technical field of image segmentation and deep learning, and discloses an automatic diet management method and device based on image segmentation and a stacking model. According to the method, an acquired food image is segmented based on a food image segmentation model, and a food area and a container area can be accurately segmented; calculating a scale factor of a pixel distance and a real distance in the food image according to a preset reference object; according to the food area, the container area and the scale factor, a food stacking model is established and used for estimating the food volume, and the quantity estimation error caused by subjective judgment in diet management is effectively avoided; and finally, identifying the food type of the food image, and estimating the nutritional ingredient content according to the food type and the food volume, so that accurate nutritional ingredient intake evaluation can be realized, manpower and material resource costs for diet ma