Journal
JOURNAL OF FOOD MEASUREMENT AND CHARACTERIZATION
Volume 11, Issue 2, Pages 538-547Publisher
SPRINGER
DOI: 10.1007/s11694-016-9421-1
Keywords
Food color; Computer vision; Digital images; Image processing; Color calibration
Categories
Funding
- Consejo Nacional de Investigaciones Cientificas y Tecnicas (CONICET) from Argentina [PIP 11220120100180]
- Agencia Nacional de Promocion Cientifica y Tecnologica from Argentina [ANPCyT PICT 2013-1637]
- Universidad Nacional de La Plata (UNLP) from Argentina [I183]
- Austrian Science Fund (FWF) [I183] Funding Source: Austrian Science Fund (FWF)
Ask authors/readers for more resources
The aim of this work was to compare two food color measurement techniques, the traditional tristimulus colorimeter and an image analysis system. In this sense a computer vision system was developed, consisting of a digital camera, a controlled illumination environment, and a software package to process the images. The conversion between color spaces was performed employing empirical mathematical models; a standard color chart was used for its calibration. The color of 40 samples of raw and processed foods was measured in the CIELAB color space with the computer vision system and a colorimeter. The equivalence between both techniques, for individual L*, a* and b* values, was determined using appropriate hypothesis tests. For most samples both systems provide equivalent results, although the total color difference.. was high enough to be noticeable. The average.. was 5.88 +/- 3.32, with an average absolute Delta L* = 2.79 +/- 2.42, Delta a* = 3.02 +/- 2.94; Delta b* = 2.84 +/- 2.53. In addition, the color measured by the image analyses technique seemed to be more similar to the real ones.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available