International Journal of Engineering Trends and Technology (IJETT) – Volume 4 Issue 10 - Oct 2013 ISSN: 2231-5381 http://www.ijettjournal.org Page 4388 Linear Image Fusion With Using Gabor Filter Mandeep Kaur * , Rajveer Kaur ** *(M.Tech Student Department Of ECE Guru Kashi University Talwandi Sabo,BATHINDA,PUNJAB,INDIA) **(Astt. Prof. Department Of ECE Guru Kashi University Talwandi Sabo, BATHINDA,PUNJAB,INDIA) Abstract— Contrast enhancement has an important role in image processing applications. Conventional contrast enhancement techniques either often fail to produce satisfactory results for a broad variety of low-contrast images, or cannot be automatically applied to different images, because their parameters must be specified manually to produce a satisfactory result for a given image. This paper proposes a new automatic method for contrast enhancement with Gabor Filter. The basic procedure is to first group the histogram components of a low-contrast image into a proper number of bins according to a selected criterion, then redistribute these bins uniformly over the grayscale, and finally ungroup the previously grouped gray-levels. This thesis presents an approach to detail aware contrast enhancement with linear image fusion and Gabor Filter. The proposed approach is abbreviated as DACE/LIF. Two main stages are involved in the DACE/LIF approach: the conventional histogram equalization (CHE) and linear image fusion (LIF). Though the CHE has the problem of over enhancement, it is noted that the details which is not obvious in the original image are generally revealed after the CHE. Interesting enough, the details shown in the original image and in the equalized image are of a kind of complementary property. Keywords— Linear image fusion(LIF),Conventional histogram equalization(CHE),Gabor Filter,Image fusion. I. INTRODUCTION An objective of image enhancement is to improve the visual quality of images. Among image enhancement schemes, contrast enhancement is a popular approach and has been widely used in many display related fields, such as consumer electronics, medical analysis, and so on. It is well-known that the contrast in an image is related to its dynamic range of histogram distribution. That is, an image with wider histogram dynamic range generally has better contrast. Consequently, to enhance the contrast in an image can be achieved by expanding its histogram distribution. Because of its simplicity, the conventional histogram equalization (CHE) is very popular which expands the histogram to its admissible extremes. Though the image contrast is enhanced, however a poor equalized image may be obtained because of the unsuitable histogram distribution for the CHE. Note that the visual quality of histogram equalized image can be improved by restricting the dynamic range or by modifying the original histogram distribution. Recently, several HE based approaches have been presented to improve the performance of the CHE. The high amplitude of the histogram components corresponding to the image background also often prevents the use of the HE techniques, which could cause a washed-out effect on the appearance of the output image and/or amplify the background noise. Figs. 1 and 2 show examples of low-contrast images and the results of treating them with conventional contrast enhancement techniques. Fig. 1(a) shows an original low-contrast image of the Mars moon, Photos, and Fig. (a) its histogram. Fig. 1(b) is the result of HE, exhibiting a washed-out appearance which is not acceptable for many applications. The cause for the washed-out appearance is that the left half of the grayscale on the histogram of the equalized image is simply empty, as shown in Fig. (b). Fig. (c) is the resulting image of histogram specification, and Fig. (c) its histogram, which is better than the HE result, but still has an unsatisfactory appearance. Fig. 1. Mars moon—Photos. (a) Low-contrast original image. (b) Result of HE, which has a washed-out appearance. (c) Result of histogram specification, though better than the HE result, still has an unsatisfactory appearance. Moreover, this technique is not automatic; the desired histogram profile must