Image enhancement with contrast coefficients using wavelet based image fusion

Abstract

The future is mainly focused on image brightness and the capacity that required storing the image. The sharp images provide better information than the blur images. To overcome from the blurriness in the image, we use image enhancement techniques. Image fusion used to overcome information loss in the image. This paper is provided with image enhancement and fusion by applying wavelet transform technique. Wavelet transform is mainly used because due to its inherent property that is they are redundant and shift invariant. It transforms the image into different scales. Image enhancement will be decided based on the levels of transformation. Low contrast results from poor resolution, lack of dynamic range, wrong settings of sensor lens during acquisition and poor quality of cameras and sensors. To avoid the information loss there is an interesting solution that is for the pictures of the same image but focused on different regions. Then using image fusion concept, all images which are captured are combined to get a single image which contains the properties of both the source images. The image entropy is composed to determine the quality of the image. The paper shows the image fusion method for both multi-resolution and images captured at different temperatures.

[Retracted] Exploring Wavelet Transform‐Based Image Enhancement Algorithm for Image Restoration of Long March National Cultural Park

“…Pardhasaradhi et al directly used the degraded system function that causes image degradation as prior knowledge and calculated the inverse permutation function of this function to recover the blurred image without considering the noise factor that forms the blurred image [ 16 ]. Ashwini proposed a multi-frame Wiener filtering method to address spatial and temporal correlation, which is a new development in Wiener filtering in recent years [ 17 ].…”

Camouflaged Foreground Detection with Fusion Methods

“…Here the pixel blocks are formed so, that if the block size increases then level also increases. By reducing noise, the new functions of likelihood are: [19][20][21] Where f(.) maps the result from wavelet domain to image domain, which is a linear processing .…”