COLOR CHILD: A robust and computationally efficient Color Image Local Descriptor

Designing a robust image local descriptor for the purpose of pattern recognition and classification has been an active area of research to date. In this paper a robust and computationally efficient Color moments augmented Cumulative Histogram-based Image Local Descriptor called COLOR CHILD has been proposed. The above descriptor has outperformed all the image local descriptors of parametric and non-parametric types quoted as recently as April 2013 in the literature for texture classification. We have demonstrated the efficacy of the proposed descriptor on a variety of benchmark texture databases such as KTH-TIPS2-a, KTH-TIPS2-b, and CuReT under both noiseless and noisy conditions.