TY - CONF AU - Miguel Oliveira AU - Angel Sappa AU - V. Santos A2 - ICIAR PY - 2012// TI - Color Correction using 3D Gaussian Mixture Models T2 - LNCS BT - 9th International Conference on Image Analysis and Recognition SP - 97 EP - 106 VL - 7324 IS - I PB - Springer Berlin Heidelberg N2 - The current paper proposes a novel color correction approach based on a probabilistic segmentation framework by using 3D Gaussian Mixture Models. Regions are used to compute local color correction functions, which are then combined to obtain the final corrected image. The proposed approach is evaluated using both a recently published metric and two large data sets composed of seventy images. The evaluation is performed by comparing our algorithm with eight well known color correction algorithms. Results show that the proposed approach is the highest scoring color correction method. Also, the proposed single step 3D color space probabilistic segmentation reduces processing time over similar approaches. SN - 0302-9743 SN - 10.1007/978-3-642-31295-3_12 L1 - http://refbase.cvc.uab.es/files/OSS2012a.pdf UR - http://dx.doi.org/10.1007/978-3-642-31295-3_12 N1 - ADAS ID - Miguel Oliveira2012 ER -