Title :
Food image analysis: Segmentation, identification and weight estimation
Author :
Ye He ; Chang Xu ; Khanna, Neha ; Boushey, Carol J. ; Delp, Edward J.
Author_Institution :
Sch. of Electr. & Comput. Eng., Purdue Univ., West Lafayette, IN, USA
Abstract :
We are developing a dietary assessment system that records daily food intake through the use of food images taken at a meal. The food images are then analyzed to extract the nutrient content in the food. In this paper, we describe the image analysis tools to determine the regions where a particular food is located (image segmentation), identify the food type (feature classification) and estimate the weight of the food item (weight estimation). An image segmentation and classification system is proposed to improve the food segmentation and identification accuracy. We then estimate the weight of food to extract the nutrient content from a single image using a shape template for foods with regular shapes and area-based weight estimation for foods with irregular shapes.
Keywords :
feature extraction; food products; image classification; image segmentation; area-based weight estimation; daily food intake records; dietary assessment system; feature classification; feature extraction; food image analysis tools; food image identification accuracy improvement; food image segmentation accuracy improvement; food image weight estimation; food shape template; food type identification; image classification system; irregular shaped foods; nutrient content extraction; regular shaped foods; Accuracy; Cameras; Estimation; Image color analysis; Image segmentation; Shape; Three-dimensional displays; Dietary Assessment; Image Segmentation; Object Identification; Weight Estimation;
Conference_Titel :
Multimedia and Expo (ICME), 2013 IEEE International Conference on
Conference_Location :
San Jose, CA
DOI :
10.1109/ICME.2013.6607548