Classification of artificial light sources and estimation of Color Rendering Index using RGB sensors, K Nearest Neighbor and Radial Basis Function


Share / Export Citation / Email / Print / Text size:

International Journal on Smart Sensing and Intelligent Systems

Professor Subhas Chandra Mukhopadhyay

Exeley Inc. (New York)

Subject: Computational Science & Engineering , Engineering, Electrical & Electronic


eISSN: 1178-5608



VOLUME 8 , ISSUE 3 (September 2015) > List of articles

Classification of artificial light sources and estimation of Color Rendering Index using RGB sensors, K Nearest Neighbor and Radial Basis Function

J.-S. Botero V. * / F.-E. López G. * / J.-F. Vargas B. *

Keywords : Color Rendering Index, CRI, light sources, Correlated Color Temperature, CCT, K Nearest Neighbor, Radial Basis Function, RBF, RGB sensors.

Citation Information : International Journal on Smart Sensing and Intelligent Systems. Volume 8, Issue 3, Pages 1,505-1,524, DOI:

License : (CC BY-NC-ND 4.0)

Received Date : 15-May-2015 / Accepted: 25-July-2015 / Published Online: 01-September-2015



Three types of artificial light sources work with electricity: incandescent, fluorescent and LED. These sources require characterization processes to allow selecting the most suitable for the application, to evaluate their capacity or more recently to tune and adjust their replicability using control algorithms. Therefore, it has been necessary to develop indices that represent these capabilities. The Color Rendering Index (CRI) is a measure used to characterize the color reproducibility of a light source in comparison to an ideal light source. The Correlated Color Temperature (CCT) is used to characterize light sources by representing the color as the temperature of a black body in Kelvin that shows nearly the same chromaticity as the analyzed light source. Using spectral information to determine the values in the XYZ space and deriving the calculation described in the standard is the best way to estimate the value of the CCT and the CRI. In this work, we implement a method to classify light sources and to select an estimation model of the CRI and the CCT using a low cost RGB sensor. The model estimation has been developed in this work and a separated algorithm for each source type has been built. The results show that using a K-Nearest Neighbor classifier, the error resulted less than $3.6%$. The error of the model estimation for the LED was 1.8%, for fluorescent light sources 0.09% and 1.2% for incandescent light sources.

Content not available PDF Share



[1] M. Ashe, D. Chwastyk, C. de Monasterio, M. Gupta, M. Pegors, 2010 U .S. Lighting Market Characterization, 2012.
[2] P.J. Bouma, Physical Aspects of Colour: An Introduction to the Scientific Study of Colour Stimuli and Colour Sensations, (1948) 312.
[3] M.S. Rea, J.P. Freyssinier-Nova, Color rendering: A tale of two metrics, Color Res. Appl. 33 (2008) 192–202. doi:10.1002/col.20399.
[4] G. Sharma, Digital Color Imaging: Handbook, CRC Press, Boca Raton, 2003.
[5] Á. Borbély, Á. Sámson, J. Schanda, The concept of correlated colour temperature revisited, Color Res. Appl. 26 (2001) 450–457. doi:10.1002/col.1065.
[6] G. De Graaf, R.F. Wolffenbuttel, Optical CMOS sensor system for detection of light sources, Sensors Actuators A Phys. 110 (2004) 77–81. doi:10.1016/j.sna.2003.10.046.
[7] C.S. McCamy, Correlated color temperature as an explicit function of chromaticity coordinates, Color Res. Appl. (1992) 142–144.
[8] G. He, J. Xu, H. Yan, Spectral optimization of warm-white light-emitting diode lamp with both color rendering index (CRI) and special CRI of R9 above 90, AIP Adv. 1 (2011) 032160. doi:10.1063/1.3644342.
[9] N. Thejokalyani, S.J. Dhoble, Novel approaches for energy efficient solid state lighting by RGB organic light emitting diodes – A review, Renew. Sustain. Energy Rev. 32 (2014) 448–467. doi:10.1016/j.rser.2014.01.013.
[10] K.A.G. Smet, W.R. Ryckaert, M.R. Pointer, G. Deconinck, P. Hanselaer, A memory colour quality metric for white light sources, Energy Build. 49 (2012) 216–225. doi:10.1016/j.enbuild.2012.02.008.
[11] K.-C. Lee, S.-H. Moon, B. Berkeley, S.-S. Kim, Optical feedback system with integrated color sensor on LCD, Sensors Actuators A Phys. 130-131 (2006) 214–219. doi:10.1016/j.sna.2006.01.028.
[12] J.S. Bajić, D.Z. Stupar, B.M. Dakić, M.B. Živanov, L.F. Nagy, An absolute rotary position sensor based on cylindrical coordinate color space transformation, Sensors Actuators A Phys. 213 (2014) 27–34. doi:10.1016/j.sna.2014.03.036.
[13] T. Fu, Z. Yang, L. Wang, X. Cheng, M. Zhong, C. Shi, Measurement performance of an optical CCD-based pyrometer system, Opt. Laser Technol. 42 (2010) 586–593. doi:10.1016/j.optlastec.2009.10.008.
[14] M. Assaad, I. Yohannes, A. Bermak, D. Ginhac, F. Meriaudeau, Design and characterization of automated color sensor system, Int. J. Smart Sens. Intell. Syst. 7 (2014) 1–12.
[15] H. Escid, M. Attari, M. Ait, W. Mechti, 0 . 35 μm CMOS optical sensor for an integrated transimpedance circuit, Int. J. Smart Sens. Intell. Syst. 4 (2011) 467–481.
[16] K. Ogawa, S. Suzuki, M. Sonehara, T. Sato, K. Asanuma, Optical probe current sensor module using the Kerr effect and its application to IGBT switching current measurements, Int. J. Smart Sens. Intell. Syst. 5 (2011) 594–598. doi:10.1109/ICSensT.2011.6137050.
[17] A. Pandharipande, D. Caicedo, Daylight integrated illumination control of LED systems based on enhanced presence sensing, Energy Build. 43 (2011) 944–950. doi:10.1016/j.enbuild.2010.12.018.
[18] J.S. Sandhu, A.M. Agogino, A.K. Agogino, Wireless sensor networks for commercial lighting control: decision making with multi-agent systems, in: AAAI Work. Sens. Networks, Citeseer, 2004: pp. 131–140.
[19] M. Ashibe, M. Miki, T. Hiroyasu, Distributed optimization algorithm for lighting color control using chroma sensors, in: 2008 IEEE Int. Conf. Syst. Man Cybern., IEEE, Singapore, 2008: pp. 174–178. doi:10.1109/ICSMC.2008.4811270.
[20] J.-S. Botero V., F.-E. López G., J.-F. Vargas B., Calibration method for Correlated Color Temperature (CCT) measurement using RGB color sensors, in: Image, Signal Process. Artif. Vis. (STSIVA), 2013 XVIII Symp., IEEE, Bogotá, 2013: pp. 3–8. doi:10.1109/STSIVA.2013.6644921.
[21] J.-S. Botero V., F.-E. López G., J.-F. Vargas B., Calibration Method for Measuring the Color Rendering Index (CRI) using RGB Sensor, Tecnológicas. EE (2013) 325–338.
[22] M. Yu, Intelligent neural network control strategy, Int. J. Smart Sens. Intell. Syst. 8 (2015) 1406–1423.
[23] J. Qi, J. Cai, Error modeling and compensation of 3d scanning robot system based on pso-rbfnn, Int. J. Smart Sens. Intell. Syst. 7 (2014) 837–855.
[24] CIE, Selected Colorimetric Tables, (2013).
[25] J.S. Botero V., L.G. Morantes G., Estimación de distancia con sensores ópticos reflexivos usando redes neuronales con funciones de base radial para aplicaciones embebidas, Ing. Y Univ. 17 (2013) 27–40.
[26] R. Srividya, C.P. Kurian, White light source towards spectrum tunable lighting — A review, in: IEEE (Ed.), 2014 Int. Conf. Adv. Energy Convers. Technol., IEEE, Manipal, 2014: pp. 203–208. doi:10.1109/ICAECT.2014.6757088.
[27] M. Aldrich, Dynamic Solid State Lighting, Massachusetts Institute of Technology, 2010.
[28] M. Aldrich, N. Zhao, J.A. Paradiso, Energy efficient control of polychromatic solid state lighting using a sensor network, in: SPIE 7784, Tenth Int. Conf. Solid State Light., SPIE, 2010. doi:10.1117/12.860755.
[29] M. Aldrich, A. Badshah, B. Mayton, N. Zhao, J.A. Paradiso, Random walk and lighting control, in: 2013 IEEE Sensors, IEEE, Baltimore, 2013: pp. 1–4. doi:10.1109/ICSENS.2013.6688590.
[30] S. Afshari, S. Mishra, A. Julius, F. Lizarralde, J.D. Wason, J.T. Wen, Modeling and control of color tunable lighting systems, Energy Build. 68 (2014) 242–253. doi:10.1016/j.enbuild.2013.08.036.