IRD India



Detection of Brain Tumour using Brightness Preserving Dynamic Fuzzy Histogram Equalization1Hemant Kaur, 2Gurmeet Kaur, 3Beant Kaur1M. Tech Student, Department of Electronics & Communication Engineering, Punjabi University, Patiala, India2Faculty, Department of Electronics & Communication Engineering, Punjabi University, Patiala, India3Faculty, Department of Electronics & Communication Engineering, Punjabi University, Patiala, IndiaEmail: hemantkaur14@ABSTRACT:In this research paper we proposed a novel technique for detection of brain tumour by using brightness preserving dynamic fuzzy histogram equalization. The fuzzy histogram equalization uses fuzzy statistics of digital images for their representation. The technique enables to handles the imprecision of gray level value in better way resulting the highlight to hidden as well as blur part of the images. The Brightness Preserving Dynamic Fuzzy Histogram Equalization(BPDFHE) enables us to use only two morphological operations for detection of brain tumour. Experimental result shows that the proposed method can effectively and significantly detect the brain tumour. The proposed method has been tested using 6 gray scale images and gives better results as compared to the conventional methods.Keywords-Image Enhancement, Fuzzy Logic, Fuzzy Image Processing, GHE, BPDHE, BPDFHE.I. INTRODUCTIONHistogram equalization?is a method in?image processing?of?contrast?adjustment using the image’s histogram. This method usually increases the global?contrast?of many images, especially when the usable?data?of the image is represented by close contrast values. The histogram shows how many times a particular grey level appears in an image. Histogram equalization transforms the intensity values so that histogram of output image approximately matches the uniform histogram[1]. For the purpose of image analysis and pattern recognition there is always a need to transform an image into another better represented form. During the past five decades image processing techniques have been developed tremendously and mathematical morphology in particular has been continuously developing because it is receiving a great deal of attention because it provides a quantitative description of geometric structure and shape and also a mathematical description of algebra, topology, probability, and integral geometry [2]. Mathematical morphology is extremely useful in many image processing and analysis applications. Mathematical morphology denotes a branch of biology that deals with the forms and structures of animals and plants.Mathematical morphology is a tool for extracting image components that are useful in representation and description of region shape, such as boundaries, skeletons and convex hull. The technique was originally developed by Mat heron and Serra at Cole des mines in Paris. The language of mathematical morphology is set theory and sets in mathematical morphology represent objects in an image. It is also useful for pre and post processing techniques. Mathematical morphology is a theory of image transformations and image functional. Morphological operations are based on simple expanding and shrinking operations. Mathematical morphology examines the geometrical structure of an image by probing it with small patterns, called structuring element, of varying sizes and shapes. This procedure results in non-linear image operators which are well suited to exploring geometrical and topological structures. Different applications of mathematical morphology are Image Enhancement, Image Segmentation, Image Restoration, Edge Detection, texture analysis. It analyses the shapes and forms of objects. In computer vision, it is used as a tool to extract image components that are useful in the representation and description of object shape. It is mathematical in the sense that the analysis is based on set theory, topology, lattice algebra, function, and so on [3-7]. Another use of mathematical morphology is to filter image. It is well known non-linear filter for image enhancement.Image Segmentation is separation of structures of interest from the Background and each other. Another way of extracting and representing information from an image is to group pixels together into regions of similarity. Importance of Image segmentation: Fully automatic brain tissue classification from magnetic resonance images (MRI) is of great importance for research and clinical studies of the normal and diseased human brain. Segmentation of medical imagery is a challenging problem due to the complexity of the images. II IMAGE CONTRAST ENHANCEMENT TECHNIQUESThere are many techniques available for image contrast enhancement; the techniques that use first order statistics of digital images (image histogram) are very popular. Global Histogram Equalization (GHE) [1] is one such widely used technique. GHE is employed for its simplicity and good performance over variety of images. However, Global Histogram Equalization(GHE)introduces major changes in the image gray level when the spread of the histogram is not significant and cannot preserve the mean image-brightness which is critical to consumer electronics applications. Its limitations are overcome by dynamic histogram equalization. The Dynamic Histogram Equalization (DHE) technique takes control over the effect of traditional Histogram Equalization so that it performs the enhancement of an image without making any loss of details in it. DHE divides the input histogram into number of sub-histograms until it ensures that no dominating portion is present in any of the newly created sub-histograms. Then a dynamic gray level (GL) range is allocated for each sub-histogram to which its gray levels can be mapped by Histogram Equalization. This is done by distributing total available dynamic range of gray levels among the sub-histograms based on their dynamic range in input image and cumulative distribution (CDF) of histogram values. This allotment of stretching range of contrast prevents small features of the input image from being dominated and washed out, and ensures a moderate contrast enhancement of each portion of the whole image. At last, for each sub-histogram a separate transformation function is calculated based on the traditional HE method and gray levels of input image are mapped to the output image accordingly. The whole technique can be divided in three parts, partitioning the histogram, allocating GL ranges for each sub-histogram and applying histogram equalization on each of them [8].The Brightness Preserving Bi-Histogram Equalization(BBHE). This method divides the image histogram into two parts. In this method, the separation intensity construct the input image. After this separation process, these two histograms are independently equalized. By doing this, the mean brightness of the resultant image will lie between the input mean and the middle gray level [9]. The histogram with range from 0 to L-1 is divided into two parts, with separating Intensity XT. This separation produces two histograms. The first histogram has the range of 0 to XT, while the second histogram has the range of XT+1 to L-1.The brightness preserving dynamic histogram equalization (BPDHE), which is an extension to Histogram Equalization that can produce the output image with the mean intensity almost equal to the mean intensity of the input, thus fulfils the requirement of maintaining the mean brightness of the image [10]. This method is actually an extension to both MPHEBP and DHE. Similar to MPHEBP, the method partitions the histogram based on the local maximums of the smoothed histogram. However, before the histogram equalization taking place, the method will map each partition to a new dynamic range, similar to DHE. As the change in the dynamic range will cause the change in mean brightness, the final step of this method involves the normalization of the output intensity. So, the average intensity of the resultant image will be same as the input. With this criterion, BPDHE will produce better enhancement compared with MPHEBP, and better in preserving the mean brightness compared with DHE [11]. III FLOW OF ALGORITHMThe flowchart for detection of Brain Tumour using Brightness Preserving Dynamic Fuzzy Histogram Equalization is as follow.Fig. 1 Flow of algorithmIn this algorithm in first step Fuzzy Histogram Computation is done using delta membership function. Fuzzy statistics is able to handle the inexactness of gray values in a better way. The next step involves Partitioning of the Histogram. It includes Detection of Local Maxima and further partitions are created. In next step Dynamic histogram equalization takes place which includes mapping partitions to dynamic range and equalizing each sub histogram. The next step involves Normalization of image histogram. In next step the Region based edge detection is done. Next we find gradient of the image. Then we perform erosion and dilation over the image and as a output we get segmented image[12].IV. EXPERIMENTAL RESULTSIn this section, we present some experimental results of our proposed method, together with Global histogram equalization (GHE), Brightness Preserving Dynamic Fuzzy Histogram Equalization (BPDHE) for comparison. The original image, together with the results based on GHE, BPDHE and BPDFHE, are shown in Fig.2 to Fig. 7Here (a) represents the original image,(b)represents the GHE image,(c)represents the BPDHE image and (d) represents the BPDFHE image.(a) (b) (c) (d)Fig. 2(a) Shows the original image (b) Shows the segmented image using GHE (c) Shows the segmented image using BPDHE (d) Shows the segmented image using BPDFHE(a) (b) (c) (d)Fig. 3(a) Shows the original image (b) Shows the segmented image using BPDHE (c) Shows the segmented image using GHE (d) Shows the segmented image using BPDFHE (b)(c) (d)Fig.4 (a) Shows the original image (b) Shows the segmented image using GHE (c) Shows the segmented image using BPDHE (d) Shows the segmented image using BPDFHE.(a) (b)(c) (d)Fig. 5 (a) Shows the original image (b) Shows the segmented image using BPDHE (c) Shows the segmented image using GHE (d) Shows the segmented image using BPDFHE(a) (b)(c) (d)Fig. 6 (a) Shows the original image (b) Shows the segmented image using BPDHE (c) Shows the segmented image using GHE (d) Shows the segmented image using BPDFHE (a) (b) (c) (d) Fig. 7 (a) Shows the original image (b) Shows the segmented image using BPDHE (c) Shows the segmented image using GHE (d) Shows the segmented image using BPDFHEDiscussion: Above figures shows the results of different histogram equalization techniques namely GHE,BPDHE and BPDFHE and it can be concluded that the results of BPDFHE are much better than the traditional methods of GHE and BPDHE. Moreover, our proposed algorithms are having good segmentation results than GHE and BPDHE.TABLE I : COMPARISON OF DIFFERENT METHODS USING PSNR PARAMETER.IMAGE GHEBPDHEBPDFHEIMAGE 111.860223.968130.0147IMAGE 29.780121.360929.9681IMAGE 39.968121.125028.7805IMAGE 410.567022.345929.5631IMAGE 510.440622.450627.2308IMAGE 611.349023.451230.6513Discussion: The above table shows comparison of various techniques using PSNR. Here, we can see that PSNR is increasing. It means that by using our proposed method our peak signal to noise ratio is increasing and this gives the best result.V CONCLUSIONIn this paper a novel technique for detection of brain tumourhas been proposed using brightness preserving dynamic fuzzy histogram equalization. We have tested our algorithm over 6 gray scale images, and 100% segmentation is achieved. This shows that our proposed technique is more efficient than the any other technique existing in literature.REFERENCES[1] R. C. Gonzalez and R. E. Woods, Digital Image Processing, 2nd edition, Prentice Hall, 2002.[2] Xianghua Hou, Honghai Liu, “WeldingImage Edge Detection and Identification Research Based on Canny Operator”,International Conference on Computer Science and Service System,2012.[3] Weifeng Zhong, Chaoqun Qin ,Chengji Liu, Huazhong Li,Hongmin Wang, “The Edge Detection of Rice Image Based on Mathematical Morphology and Wavelet Packet”,Intemational Conference on Measurement, Information and Control (MIC),2012.[4] Zhonghai li, zhihui yang, wenlong wang, jianguo cui , “An adaptive threshold edge detection method based on the law of gravity” IEEE,2013.[5]Erdo?an Aldemir, Nerhun Yildiz, “Design of an Automatic Target Recognition Algorithm”, IEEE,2013.[6] Suman Rani, Beant Kaur, Deepti Bansal, “Detection of Edges Using Image Processing”, International Conference on Emerging Technologies in Electronics and Communication,2013.[7] J.Serra, Ed., “Image Analysis and Mathematical Morphology”, vol. 2: Theoretical Advances, New York Academic, 1988[8] M. Abdullah-Al-Wadud, Md. Hasanul Kabir, M. Ali Akber Dewan, and Oksam Chae , “A dynamic histogram equalization for image contrast enhancement”, IEEE Trans. Consumer Electron, vol. 53, no. 2, pp. 593- 600, 2007.[9] Yeong-Taeg Kim , “Contrast enhancement using brightness preserving Bi-Histogram equalization”, IEEETrans. Consumer Electronics, vol. 43, no. 1, pp. 1-8, 1997.[10] A. Jayachandran, R. Dhanashakeran et al. ,“Fuzzy Information System based Digital Image Segmentation by Edge Detection”, IEEE, 2010.[11] H. Ibrahim, and Nicholas Sia Pik Kong , “Brightness preserving dynamic histogram equalization for image contrast enhancement”, IEEETrans. Consumer Electronics, vol. 53, no. 4, pp. 1752 – 1758, 2007.[12]D. Sheet and H. Garud, “Brightness Preserving Dynamic Fuzzy Histogram Equalization”,IEEE Trans., Consumer Electronics, vol. 56, no. 4, Nov. 2010. ................
................

In order to avoid copyright disputes, this page is only a partial summary.

Google Online Preview   Download