Computer vision system approach in colour measurements of foods: Part I. development of methodology

Abstract

The colour assessment ability of the computer vision system is investigated and the data are compared with colour measurements taken by a conventional colorimeter. Linear and quadratic models are built to improve currently used methodology for the conversion of RGB colour units to L * a * b * colour space. For this purpose, two innovative ideas are proposed and tested. First, substantial amount of colour tones is generated to cover as many points in the colour space as possible. Secondly, the colour space is calibrated separately, whereas in previous research in the literature, the colour space is calibrated simultaneously. It is found that the RGB colour units to L * a * b * colour space transformation approach proposed in this study is more logical and more accurate, and the prediction performance of the quadratic model is superior over the linear model. Keywords

Computer vision system approach in colour measurements of foods: Part II. validation of methodology with real foods

“…In this study, the RGB colour analysis was done using a digital image acquisition system developed in Tarlak et al (2016). The L * a * b * food colour analysis was performed randomly via twenty different measurements from the surfaces of the selected foods using a Konica Minolta Chroma Meter CR-400 equipped with D 65 illuminant.…”

“…The main objective of the present work was to implement and validate the proposed methodology given in Tarlak et al (2016) …”

Applications of artificial neural networks in three agro-environmental systems: microalgae production, nutritional characterization of soils and meteorological variables management

“…Regarding the hardware for MV, the acquisition system is usually composed of three main components: a color digital camera, an illumination source, and an image processing software. The lighting source must provide uniform and consistent illumination across the sample to photograph, color temperature is also considered and usually fixed around 5,000 K to 5,500 K. To ensure uniform illumination conditions, multiple light sources can be employed as long as they are homogeneous (Tarlak et al, 2016;Valous et al, 2009). The camera is usually located at a certain distance so that the measurement does not interfere with the illumination since the resulting images are highly affected by the light (ten Bosch and Coops, 1995).…”

“…The RGB to L*a*b* color transformation can be performed through several methods such as equation systems (Barbin et al, 2016), quadratic models, (Tarlak et al, 2016), linear models and ANN (Afshari-Jouybari and Farahnaky, 2011). Between these methods, ANN present remarkable results for this conversion (Afshari-Jouybari and Farahnaky, 2011; León et al, 2006;Pedreschi et al, 2006 Pothula et al, 2015).…”

“…Each time the user wants to measure the color of images in different scenarios -different lighting conditions and camera configuration, it is necessary to take a picture of the colorchecker in each different scenario. Otherwise, errors in the L*a*b* color conversion will take place due to the differences caused by light variations (Tarlak et al, 2016;ten Bosch and Coops, 1995;Valous et al, 2009) and cameras color acquisition (Ilie and Welch, 2005;Kim et al, 2012). The recommended colorchecker to use with the DigiCIELAB software is the "X-Rite ColorChecker Classic" (Figure 23, Appendix C).…”