To search, Click below search items. |
| All Published Papers Search Service |
|
|
|
Title |
Illumination Reflectance Based Color Image Contrast Enhancement using Wavelets and SVD |
|
Author |
K. Punnnam Chandar |
| Citation |
Vol. 25 No. 7 pp. 212-218 |
|
Abstract |
Loss of details and the ‘halos’ is the disadvantage with multiscale retinex with color restoration image enhancement. To overcome this disadvantage, a new color image enhancement technique based on processing the reflectance component using Discrete Wavelet and Singular Value Decomposition is proposed in this paper. The real color image is transformed from RGB to HSV. The Value component is decomposed in to illumination and reflectance (IR) using homomorphic filtering. The reflectance component is accounted for the Contrast and is one scale decomposed using discrete wavelet transform in to low frequency and high frequency sub bands. The variation of Contrast in low frequency band is corrected using Singular Value Decomposition, and then inverse wavelet transform is applied to reconstruct the reflectance, preserving the details (high frequencies) of the image. Lastly saturation is attenuated using low pass Butterworth filter to suit the color perceiving of human vision system. The experimental results with the proposed technique show that the color images are enhanced with details preserved and ‘halos’ restrained. To indicate the efficacy of the proposed true color image contrast enhancement algorithm quantitative measurements, discrete entropy, relative entropy and mutual information are computed. |
|
Keywords |
Color Images, Contrast Enhancement, HSV, Homomorphic Filtering, Discrete Wavelet Transform, , SVD. |
|
URL |
