Hue-Preserving Color Image Enhancement Without Gamut Problem

Sarif Kumar Naik and C. A. Murthy

E-mail : {sarif_r, murthy}
Machine Intelligence Unit
Indian Statistical Institute

Abstract : (IEEE Trans. on Image Processing, vol. 12, no.12, pp. 1591-1598, December, 2003. See IEEE Copyright Notice)

        The first step in many techniques for processing intensity and saturation in color images keeping hue unaltered, is to transform the image data from RGB space to other color spaces such as LHS, HSI, YIQ, HSV etc. Transforming from one space to another and processing in these spaces generate gamut problem, i.e., the values of the variables may not be in their respective intervals. Enhancement techniques for color images are studied here in a generalized setup. A principle is suggested to make the transformations gamut problem free in this regard. Using the same principle a class of hue preserving contrast enhancement transformations are proposed, which generalize the existing gray level contrast  intensification techniques to color images. These transformations are also seen to bypass the above mentioned color co-ordinate transformations for image enhancement. The developed principle is used to generalize the histogram  equalization scheme for gray scale images to color images.

Full Text[PDF]

Results :

Original Images

org_lenna.gif (56589 bytes)org_dancer.gif (36912 bytes)org_artif.gif (3687 bytes)org_peppers.gif (47565 bytes)

Linearly Enhanced Images (proposed method)

linear_lenna.gif (56693 bytes)linear_dancer.gif (45150 bytes)linear_artif.gif (3687 bytes)linear_peppers.gif (47565 bytes)

Enhanced Images using S-type function(proposed method)

stype_2_1.5_lenna_lin.gif (55590 bytes)stype_2_1.5_dancer_lin.gif (49261 bytes)stype_2_1.5_artif_lin.gif (3687 bytes)stype_2_1.5_peppers_lin.gif (48065 bytes)

Enhanced Images using Histogram Equalization(proposed method)

equa_lenna_lin.gif (55904 bytes)equa_dancer_lin.gif (54974 bytes)equa_artif_lin.gif (3732 bytes)equa_peppers_lin.gif (49107 bytes)

Enhanced Images using Yang et al's Method(effect of saturation clipping can be seen in the artificial image with color boxes)

yanglhs_lenna.gif (52881 bytes)yanglhs_dancer.gif (52665 bytes)yanglhs_artif.gif (3582 bytes)yanglhs_peppers.gif (46679 bytes)

Enhanced Images using Weeks et al's Method

weeks_lenna_h96_i64.gif (59553 bytes)weeks_dancer_h96_i64.gif (51969 bytes)weeks_artif_h96_i64.gif (3732 bytes)weeks_peppers_h96_i64.gif (53793 bytes)


Back to Home