under construction...
Image Contrast Enhancement with Hist. Equal. and Hue Preserving
1. Histogram equalization
}When the usable data of the image is represented by close contrast values;
}Spread out the most freq. intensity values.
HE
Original
2. CLAHE (Contrast Limited Adaptive HE)
}Contrast limiting applied for each neighbor from which a transformation function is derived:
}Proportional to the cumulative distribution function (CDF) of pixel values;
}Contrast limited: clipping histogram at a predefined value before computing CDF.
}Efficient computation by interpolation: The image is partitioned into equally sized rectangular tiles.
Original
CLAHE
3. Partitioned HE
}Static partitioned HE: still use the original dynamic range
}Brightness preserving bi-HE (BBHE) [Kim’97]: divide histogram based on mean brightness and then HE for each one;
}Dualistic sub-image HE (DSIHE) [Wan’99]: median as the separation point;
}Minimum mean brightness error bi-HE (MMBEBHE) [Chen’03]: separation point based on minimum mean brightness error;
}Recursive mean-separate HE (RMSHE) [Chen’03]: recursively split into multi sub-histograms (initially from two), based on mean;
}Recursive sub-image HE (RSIHE)[Sim’07]: recursively split histogram into more sub-histograms, based on median;
}Bi-HE plateau limit [Ooi’09]: clipping based on average number of intensity occurrence.
}Dynamic partitioned HE: employ the enhanced dynamic range
}Dynamic HE [Wadud’07]: partition histogram based on local minima, and new dynamic range based on pixel number;
}Brightness preserving dynamic HE (BPDHE) [Irahim’07]: partition with local maxima, brightness normalization after HE.
4. Histogram Modification with Mean-Brightness Preservation
}Weight and threshold before HE (WTHE) [Wang&Ward’07];
}Gray-level grouping: group histogram bins and redistribute groups iteratively[Chen’06];
}Histogram modification as an optimization problem to adapt the enhancement level;
}Linear black and white (B&W) stretching: Decrease histogram bin length for dark and bright end
}Histogram smoothing for spikes: Backward-difference of histogram as measure of smoothness
}Weighted histogram approximation: Average local variance of all the pixels with the same gray-level is used to weight the approximation error, so that avoid spikes further.
5. Hue Preserving and Saturation Enhancement
}Chromaticity diagram: gamut;
}Hue preserving: HSI (hue-saturation-intensity) from RGB;
}Methods of saturation enhancement:
}1. Increase saturation by fraction;
}2. Increase saturation to the maximum based on hue and lumin.;
}3. Reduce lumin. by fraction, then increase saturat. by fraction;
}4. Reduce lumin. by fraction, then increase saturat. to maximum;
}Too strong color enhancement result in poor quality;
}Increased saturation introduces noise in uniform areas;
}“Out of gamut” problem in saturation scaling;
}Saturation clipping: clip before transform back to RGB;
}S-type transformation: nonlinear hue preserving.
}Saturation normalization: histogram equalization in normalized HSI.
Gamut in CIE-XY Chromaticity Diagram