Image enhancement: A composite image approach using contourlet transform

Most existing image enhancement algorithms work on a single image. Their performance is limited by the capacity of the sensor by which the image is originally taken. In some cases they completely fail to provide us the necessary enhancements. Here we propose a composite image enhancement approach for enhancing still images. We combine the relevant features of the input images and produce a composite image which is rich in information content. The input images are first decomposed into multiple resolutions by using the contourlet transform which provides a better representation than the conventional wavelet transforms. Transformed coefficients are combined with a predefined fusion rules. The resultant image is found by performing inverse contourlet transformation of the composite image. The results found are encouraging and the algorithm does not introduce any artificial artefacts and distortion. © 2009 IEEE.