Color of the food is the first parameter of quality evaluated by consumers. What is important is the acceptance of the product even before being consumed. Inspection of food products is done using machine vision, particularly analyzing and processing the images, where the parameters of each pixel on the surface of the recorded product must be known. Using different color spaces quantitative color value is obtained. Although there are many different color spaces, when it comes to food, the most frequently used is the CIE L*a*b* color space, due to its uniform color distribution and because its perception of color is closest to the one human eye. RGB color space, where a sensor in each pixel records the intensity of light in the red, green and blue spectrum, is also similar to human perception of colors and it is also frequently used. The problem with the L * a * b * scale is that commercial color-meters measure only a dozen of square centimetres of the product itself and the measurements are not representative for the most of heterogeneous materials. The aim of this paper is to present the analysis of images of chosen food products using the two color spaces. In each of the two color spaces, after determining the range of parameters appropriate to good quality products, the criteria for the discrimination of damaged products is defined and tested. The comparison of the applications of those criteria shows that, in the case of food, the transformation of RGB coordinates into the CIE L*a*b* color space makes it possible to achieve greater accuracy and improved calculation of appropriate color parameters.
[1]
Zhang Min,et al.
Colour vision in forest and wood engineering.
,
2000
.
[2]
Sundaram Gunasekaran,et al.
Using computer vision for food quality evaluation : Applications of immunobiosensors and bioelectronics in food sciences and quality control
,
1994
.
[3]
Roseleena Jaafar,et al.
Photogrammetric grading of oil palm fresh fruit bunches
,
2009
.
[4]
Da-Wen Sun,et al.
Recent developments in the applications of image processing techniques for food quality evaluation
,
2004
.
[5]
Stephen J. Symons,et al.
Developments in the use of image analysis for the assessment of oriental noodle appearance and colour
,
2004
.
[6]
Christopher A. Brown,et al.
CHARACTERIZATION OF FOOD SURFACES USING SCALE‐SENSITIVE FRACTAL ANALYSIS
,
2000
.
[7]
Da-Wen Sun,et al.
Inspecting pizza topping percentage and distribution by a computer vision method
,
2000
.
[8]
J. Lu,et al.
Evaluation of pork color by using computer vision.
,
2000,
Meat science.