Paper id 27201451

Paper id 27201451

• 1.
  International Journal ofResearch in Advent Technology, Vol.2, No.7, July 2014 E-ISSN: 2321-9637 138 Image Fusion with Pyramidal Decomposition Ashly Thomas1, Chinchu Glaison2 Computer Science and Engineering,St. Joseph’s College of Engineering and Technology, Pala1 ,2 Assistant Professor1, PG Scholar2 Email:[email protected] Abstract— A fast and effective image fusion method is proposed for creating a highly informative fused image through merging multiple images. The proposed method is based novel detail-enhancing exposure fusion approach with images under different exposure settings, first the fine details are extracted based on guided filter. Next, the base layers across all input images are fused using multiresolution pyramid. Exposure, contrast, and saturation measures are considered to generate a mask that guides the fusion process of the base layers. Finally, the fused base layer is combined with the extracted fine details to obtain detail-enhanced fused image. The goal is to preserve details in both very dark and extremely bright regions .Moreover, we have demonstrated that the proposed method is also suitable for the multifocus image fusion without introducing artifacts Index Terms-Guidedfilter, multiresolution. 1. INTRODUCTION IMAGE fusion is an important technique for various image processing and computer vision applications such as feature extraction and target recognition. Through image fusion, different images of the same scene can be combined into a single fused image.The fused image can provide morecomprehensive information about the scene which is more useful for human and machine perception. For instance, the performance of feature extraction algorithms can be improved by fusing multi-spectral remote sensing images . The fusion of multi-exposure images can be used for digital photography. In these applications, a good image fusion method has the following properties. First, it can preserve most of the useful information of different images. Second, it does not produce artifacts. Third, it is robust to imperfect condition such as mis-registration and noise. In single exposure, normal digital camera can collect limited luminance variations from the real world scene, which is termed as low dynamic range (LDR) image[1]. To circumvent this problem, modern digital photography offers the concept of exposure time variation to capture details in very dark or extremely bright regions, which control the amount of light allowed to fall on the sensor. Different LDR images are captured to collect complete luminance variations in rapid successions at different exposure settings known as exposure bracketing. However, each exposure will handle the small portion of the luminance variation in the entire scene. Short exposure can capture details from the bright regions (i.e., highlights) and long exposure can capture details from dark regions. 2. RELATED WORKS A large number of image fusion methods have been proposed in literature. Among these methods, multiscale image fusion[1] and data-driven image fusion are very successful methods. They focus on different data representations, e.g., multi-scale coefficient or data driven decomposition coefficients and different image fusion rules to guide the fusion of coefficients. The major advantage of these methods is that they can well preserve the details of different source images. However, these kinds of methods may produce brightness and color distortions since spatial consistency is not well considered in the fusion process. To make full use of spatial context, optimization based image fusion approaches, e.g., generalized random walks[2] and Markov random fields [7] based methods have been proposed. These methods focus on estimating spatially smooth and edge aligned weights by solving an energy function and then fusing the source images by weighted average of pixel values[3]. However, optimization based methods have a common limitation, i.e., inefficiency, since they require multiple iterations to find the global optimal solution. Moreover, another drawback is that global optimization based methods may over-smooth the resulting weights, which is not good for fusion. 3. METHODOLOGY To solve the problems mentioned above, a novel detail-enhancing exposure fusion approaches proposed. Several advantages of the proposed image fusion approach are highlighted in the following. (1) Traditional multi-scale image fusion methods require more than two scales to obtain satisfactory fusion results. The key contribution of this paper is to present a fast two-scale fusion method which does not rely heavily on a specific image decomposition method. A simple average filter is qualified for the proposed fusion framework. (2) A novel weight construction method is proposed to combine pixel saliency and spatial context for image fusion. Instead of using optimization based methods, guided filtering is adopted as a local filtering method for image fusion.
• 2.
  International Journal ofResearch in Advent Technology, Vol.2, No.7, July 2014 E-ISSN: 2321-9637 139 (3) An important observation of this paper is that the roles of two measures, i.e., pixel saliency and spatial consistency are quite different when fusing different layers. In this paper, the roles of pixel saliency and spatial consistency are controlled through adjusting the parameters of the guided filter. Fig. 1 a:input image Fig.2 b:input image Fig.3 c:input image Fig.4 d:input image Fig. 5:Our detail enhanced fusion results Fig. 1 ,2 , 3 and 4 are the input images to get the detailed enhanced result 3.1. Guided image filtering Recently, edge-preserving filters [11], have been an active research topic in image processing. Edge-preserving smoothing filters such as guided filter [8], weighted least squares , and bilateral filter can avoid ringing artifacts since they will not blur strong edges in the decomposition process. Among them, the guided filter is a recently proposed edge-preserving filter, and the computing time of which is independent of the filter size. Furthermore, the guided filter[8] is based on a local linear model, making it qualified for other applications such as image matting, up-sampling and colorization . In this paper, the guided filter is first applied for image fusion. In theory, the guided filter assumes that the filtering output O is a linear transformation of the guidance image I in a local window ωk centered at pixel k. Oi = akIi + bk ∀i ∈ωk (1) where ωk is a square window of size (2r+1)×(2r+1). The linear coefficients ak and bk are constant in ωk and can be estimated by minimizing the squared difference between the output image O and the input image P. (2) where is a regularization parameter given by the user. The coefficients ak and bk can be directly solved by linear regression (3) where μk and δk are the mean and variance of I in ωk respectively, |ω| is the number of pixels in ωk, and Pk is the mean of P in ωk. Next, the output image can be calculated all local windows centered at pixel k in the window ωi will contain pixel i. Fig.6: enhanced result
• 3.
  International Journal ofResearch in Advent Technology, Vol.2, No.7, July 2014 E-ISSN: 2321-9637 140 The block diagrammatic representation of the present detail enhanced framework is shown in Figure 1. We seek to enhance fine details in the fused image by using edge preserving filter . Edge preserving filters have been utilized in several image processing applications such as edge detection image enhancement, and noise reduction Recently, joint bilateral filter has been proposed which is effective for detecting and reducing large artifacts such as reflections using gradient projections. More recently, anisotropic diffusion has been utilized for detail enhancement in exposure fusion, in which texture features are used to control the contribution of pixels from the input exposures. In our approach, the guided filter is preferred over other existing approaches because the gradients present near the edges are preserved accurately. We use guided filter for base layer and detail layer extractions which is more effective for enhancing texture details and reducing gradient reversal artifacts near the strong edges in the fused image. Multiresolution[5] [6] approach is used to fuse computed base layers across all of the input images. The detail layers extracted from input exposures are manipulated and fused separately. The final detail enhanced fused image is obtained by integrating the fused base layer and the fused detail layer. The detailed description of the proposed approach is given in the forthcoming section. It is worth pointing out that our method essentially differs from which aims at enhancing the texture and contrast details in the fused image with a nonlinear edge preserving filter (i.e., the guided filter). Moreover, it is demonstrated that the proposed approach fuses the multifocus images effectively and produces the result of rich visual details. 3.2. Computation of laplacian and gaussian pyramid Researchers have attempted to synthesize and manipulate the features at several spatial resolutions that avoid the introduction of seam and artifacts such as contrast reversal or black halos. In the proposed algorithm, the band-pass components at different resolutions are manipulated based on weight map that determine the pixel value in the reconstructed fused base layer. The pyramid representation[4] [9] expresses an image as a sum of spatially band-passed images while retaining local spatial information in each band. A pyramid is created by low pass-filtering an image 0 with a compact two-dimensional filter. The filtered image is then subsample by removing every other pixel and every other row to obtain a reduced image 1.This process is repeated to form a Gaussian pyramid 0, 1, 2, 3, . . . , : (4) where (0 ) refers to the number of levels in the pyramid.Expanding 1 to the same size as 0 and subtracting yields the band-passed image 0. A Laplacian pyramid 0, 1, 2, . . . , −1, can be built containing band-passed images of decreasing size and spatial frequency = − +1, = 1, . . . , – 1 (5) where the expanded image +1 is given by (6) The original image can be reconstructed from the expanded band-pass images. 0= 0+ 1+ 2+ ........+ −1+ . (7) The Gaussian pyramid contains low-passed versions of the original 0, at progressively lower spatial frequencies. This effect is clearly seen when the Gaussian pyramid “levels” are expanded to the same size as 0.The Laplacian pyramid consists of band-passed copies of 0. Each Laplacian level contains the “edges” of a certain size and spans approximately an octave in spatial frequency. 3.3. Base layer fusion based on multiresolution pyramid. In our framework, the fused base layer (’, ’) computed as the weighted sum of the base layers 1(’, ’), 2(’, ’), . . . , (’, ’) obtained across input exposures. We use the pyramid approach proposed by Burt and Adelson . which generates Laplacian pyramid of the base layers { (’, ’)}and Gaussian pyramid of weight map functions { (’, ’)}estimated from three quality measures (i.e., saturation
• 4.
  (’, ’), contrast (’,’),and exposure (’, ’)). Here, (0 ) refers to the number of levels in the pyramid and (1 ) refers to the number of input images. The weight map is computed as the product of these three quality metrics (i.e., (’, ’) =
• 5.
  (, ’) . (’, ’) . (’, ’)). The { (’, ’)} multiplied with the corresponding{ (’, ’)}and summing over yield modified Laplacian pyramid ’(’, ’) as follows: (8) The (’, ’) that contains well exposed pixels is reconstructed by expanding each level and then summing all the levels of the Laplacian pyramid.
• 6.
  International Journal ofResearch in Advent Technology, Vol.2, No.7, July 2014 E-ISSN: 2321-9637 141 (9) 3.4. Detail layer fusion and manipulation The detail layers computed across all the input exposures are linearly combined to produce fused detail layer (’, ’) that yields combined texture information as follows: (10) The nonlinear function (.) is defined as (11) where is a smooth step function equal to 0 if (’, ’) is less than 1% of the maximum intensity, 1 if it is more than 2%, with a smooth transition in between, and the parameter is used to control contrast in the detail layers. We have found that = 0.2 is a good default setting for all experiments. Finally, the detail enhanced fused image (’, ’) is easily computed by simply adding up the fused base layer (’, ’) and the manipulated fused detail layer (’, ’). (’, ’) = (’, ’) + (, ’) (12) 4. EXPERIMENTAL RESULTS AND ANALYSIS 4.1. Comparison with Other Exposure Fusion Methods. Figures 1 depict examples of fused images from the multiexposure images. It is noticed that the proposed approach enhances texture details while preventing halos near strong edges. As shown in Figure 1(b), the details from all of the input images are perfectly combined and none of the four input exposures (see Figure 1(a)) reveals fine textures on the table that are present in the fused image. we compare our results to the recently proposed approaches. In our results the table texture and painting on the window are emphasized which are difficult to be visible in . Clearly, this is suboptimal as it removes Pixel-to-pixel correlations by subtracting a low-pass filtered copy of the image from the image itself to generate a Laplacian pyramid and the result is a texture and edge details reduction in the fused image[9][10]. Existing shows the results using pyramid approach which reveals many details but losses contrast and color information. Generalized random walks based exposure fusion which depicts less texture and color details in brightly illuminated region. But in proposed retains colors, sharp edges, and details while also maintaining an overall reduction in high frequency artifacts near strong edges. 5. CONCLUSION We proposed a method to construct a detail enhanced image from a set of multiexposure images by using a multiresolution decomposition technique. When compared with the existing techniques which use multiresolution and single resolution analysis for exposure fusion, the current proposed method performs better in terms of enhancement of texture details in the fused image. The framework is inspired by the edge preserving property of guided filter that has better response near strong edges. The two layer decomposition based on guided filter is used to extract fine textures for detail enhancement. Moreover, we have demonstrated that the present method can also be applied to fuse multifocus images (i.e., images focused on different targets). More importantly, the information in the resultant image can be controlled with the help of the proposed free parameters. REFERENCES [1] D. Socolinsky and L. Wolff, “Multispectral image visualization through first-order fusion,” IEEE Trans. Image Process., vol. 11, no. 8,pp. 923– 931, Aug.2002.. [2] R. Shen, I. Cheng, J. Shi, andA.Basu,“Generalized random walks for fusion of multi-exposure images,”IEEE Trans. Image Process., vol. 20,no.12,pp.36343646, Dec. 2011.. [3] S. Li, J. Kwok, I. Tsang, and Y. Wang, “Fusing images with different focuses using support vector machines,” IEEE Trans. Neural Netw.,vol. 15, no. 6, pp. 1555–1561, Nov. 2004. [4] P. Burt and E. Adelson, “The laplacian pyramid as a compact image code,” IEEE Trans. Commun., vol. 31, no. 4, pp. 532–540, Apr. 1983. [5] S. Li and X. Kang, “Fast multi-exposure image fusion with median filter and recursive filter,” IEEE Transactions on Consumer Electronics, vol. 58, no. 2, pp. 626–632, 2012. [6] W. Zhang and W.-K. Cham, “Gradient-directed multiexposure composition,” IEEE Transactions on Image Processing, vol. 21, no. 4, pp. 2318– 2323, 2012. [7] R. Shen, I. Cheng, J. Shi, and A. Basu, “Generalized random walks for fusion of multi-exposure images,” IEEE Transactions on Image Processing, vol. 20, no. 12, pp. 3634–3646, 2011. [8] K. He, J. Sun, and X. Tang, “Guided image filtering,” in Proceedings of the 11th European Conference on Computer Vision, 2010. [9] P. Perona and J. Malik, “Scale-space and edge detection using anisotropic diffusion,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 12, no. 7, pp. 629–639, 1990.
• 7.
  International Journal ofResearch in Advent Technology, Vol.2, No.7, July 2014 E-ISSN: 2321-9637 142 [10] S. Paris, S. W. Hasinoff, and J. Kautz, “Local laplacian filters: edge-aware image processing with a laplacian pyramid,” ACM Transactions on Graphics, vol. 30, no. 4, article 68, 2011. [11] A. Agrawal, R. Raskar, S. K. Nayar, and Y. Li, “Removing photography artifacts using gradient projection and flash-exposure sampling,” ACMTransaction on Graphics, vol. 24,no. 3, pp. 828– 835.