Abstract | ||
---|---|---|
Various color histogram equalization (CHE) methods have been proposed to extend grayscale histogram equalization (GHE) for color images. In this paper a new method called “histogram diffusion” that extends the GHE method to arbitrary dimensions is proposed. Ranges in a histogram are specified as overlapping bars of uniform heights and variable widths which are proportional to their frequencies. This diagram is called the “vistogram.” As an alternative approach to GHE, the squared error of the vistogram from the uniform distribution is minimized. Each bar in the vistogram is approximated by a Gaussian function. Gaussian particles in the vistoram diffuse as a nonlinear autonomous system of ordinary differential equations. CHE results of color images showed that the approach is effective. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1109/ICIP.2011.6116448 | ICIP |
Keywords | Field | DocType |
gaussian particle,color histogram equalization method,color image,mixture of gaussians,grayscale histogram equalization,ghe method,contrast enhancement,gaussian processes,nonlinear differential equations,color histogram diffusion,image enhancement,nonlinear autonomous system,gaussian function approximation,vistogram,squared error,ordinary differential equation,image colour analysis,color image processing,histogram equalization,autonomy,color,differential equations,nonlinearity,color histogram,histograms,uniform distribution,gray scale,diffusion | Histogram,Computer vision,Color histogram,Histogram matching,Adaptive histogram equalization,Artificial intelligence,Balanced histogram thresholding,Image histogram,Histogram equalization,Color normalization,Mathematics | Conference |
ISSN | ISBN | Citations |
1522-4880 E-ISBN : 978-1-4577-1302-6 | 978-1-4577-1302-6 | 1 |
PageRank | References | Authors |
0.35 | 2 | 1 |