A computer vision system for appearance-based descriptive sensory evaluation of meals

• This paper presents a complete machine vision system for automatic descriptive sensory evaluation of meals. A human sensory panel first developed a set of 72 sensory attributes describing the appearance of a prototypical meal, and then evaluated the intensities of those attributes on a data set of 58 images of example meals. This data was then used both to train and validate the performance of the artificial system. This system covers all stages of image analysis from pre-processing to pattern recognition, including novel techniques for enhancing the segmentation of meal components and extracting image features that mimic the attributes developed by the panel. Artificial neural networks were used to learn the mapping from image features to attribute intensity values. The results showed that the new system was extremely good in learning and reproducing the opinion of the human sensory experts, achieving almost the same performance as the panel members themselves. (c) 2005 Elsevier Ltd. All rights reserved.

Ämnesord

NATURVETENSKAP  -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)

NATURAL SCIENCES  -- Computer and Information Sciences -- Computer Sciences (hsv//eng)

LANTBRUKSVETENSKAPER  -- Lantbruksvetenskap, skogsbruk och fiske -- Livsmedelsvetenskap (hsv//swe)

AGRICULTURAL SCIENCES  -- Agriculture, Forestry and Fisheries -- Food Science (hsv//eng)

Nyckelord

artificial neural network

sensory descriptive evaluation

Bayes classifier

appearance

meal

image analysis

Computer science

Datavetenskap

Computer and Systems Science

Data- och systemvetenskap

Publikations- och innehållstyp

ref (ämneskategori)

art (ämneskategori)