Abstract

Efficient Color Image Enhancement Using Computational Photography Method

In this letter, we propose a new global contrast enhancementalgorithmusingthe computational pho-tography method. On the basis of the computational photography, the color and depth image are first partitionedinto subintervals using the Gaussian mixture model. The positions partitioning the color are then adjusted such that spatially neighbouringpixelswiththesimilarintensityanddepthvaluescan begroupedintothesamesub-interval.Byapproximatingthemapping curveofthecontrastenhancementforeachsub-interval,thecomprehensive image contrast can be improved without over-enhancing the local imagecontrast.Experimentalresultsdeterminetheef-fectiveness of the proposed algorithm.

PDF