AN INNOVATIVE MORPHOLOGICAL APPROACH FOR NOISE REMOVAL CUM EDGE DETECTION FOR DIGITIZED PAINTINGS

The older paintings suffer from breaks in the substrate, the paint, or the varnish. When we digitized these paintings, they can be modified using mathematical algorithms and cracks are eliminated so as to maintain the quality. The field of computer vision is concerned with extracting features and information from images in order to make analysis of images easier, so that more and more information can be extracted. The primary goal of this study is to use novel approach for noise removal cum unwanted edge from digitized paintings. The method used for both noise removal and edge detection is mathematical morphology. On the basis of set theory, mathematical morphology is used for image processing, analyzing and comprehending. It is a powerful tool in the geometric morphological analysis and description. The results exhibit that the new method overcomes the deficiency of conventional methods and efficiently removes the noise and detects the edges for digitized paintings.


INTRODUCTION
Noise removal and edge detection are the two most important steps in processing of any digital images for improving the information in the picture so that it can be easily understand by human and to make it suitable and readable for any further processing which works on those images (Karuppiah and Srivatsa, 2012). There are many edge detection methods like Sobel, Prewitt, Canny edge detectors and noise removal techniques like filters according to the type of noise present for digital image processing. With advancement in technology in image acquisition and analysis systems new methods are still required for high level of noise removal and for low contrast edge detection. Mathematical Morphology (MM) is a new mathematical theory which can be used to process and analyze the images. In the MM theory, images are treated as sets and morphological transformations which derived from Minkowski addition and subtraction are defined to extract features in images.
In this study, a new morphological approach for noise removal cum edge detection is introduced for digitized paintings. For detecting edges in an image efficiently, first the noise is to be removed. Noise is removed using morphological operations and further morphological operations are applied on this image to extract the edges.

FUNDAMENTAL OPERATIONS OF MATHEMATICAL MORPHOLOGY
On the basis of set theory, mathematical morphology is used for image processing, analyzing and comprehending. It is a powerful tool in the geometric morphological analysis and description. In the MM theory, images are treated as sets and morphological transformations which derived from Minkowski addition and subtraction are defined to Science Publications JCS extract features in images. The image which will be processed by mathematical morphology theory must be changed into set and represented as matrix.
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. It analyzes 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 (Gonzalez and Woods, 2008). Another use of mathematical morphology is to filter image. It is a well know nonlinear filter for image enhancement (Maragos, 1996;Yu-Qian et al., 2005;Xu et al., 2008).
The basic idea in binary morphology is to probe an image with a simple, pre-defined shape, drawing conclusions on how this shape fits or misses the shapes in the image. This simple "probe" is called structuring element, which is also a binary image (i.e., a subset of the space or grid). A structuring element is a small image used as a moving window whose support delineates pixel neighbourhoods in the image plane. Mathematical morphology involves geometric analysis of shapes and textures in images. An image can be represented by a set of pixels (Qiyuan et al., 2007).
The basic mathematical morphological operations namely dilation, erosion, opening, closing are used for detecting, modifying, manipulating the features present in the image based on their shape. In the following, some basic mathematical morphological operations of gray-scale images are introduced.
Let J (x, y) denote a gray-scale two dimensional image, SE denote structuring element. Dilation of a gray-scale image J(x, y), by a gray-scale structuring element SE (a, b) is denoted by Equation 1: Erosion of a gray-scale image J (x, y) by a gray-scale structuring element SE(a, b) is denoted by Equation 2: Opening and closing of gray-scale image J (x, y) by gray-scale structuring element SE(a,b) are denoted respectively by Equation 3 and 4: Erosion basically decreases the gray-scale value of an image by applying shrinking transformation, while dilation increases the gray-scale value of the image by applying expanding transformation. However, both of them are sensitive to the image edge whose gray-scale value changes obviously. Erosion filters the inner image while dilation filters the outer image. Opening is erosion followed by dilation and closing is dilation followed by erosion. Opening generally smoothes the contour of an image, breaks narrow gaps. As opposed to opening, closing tends to fuse narrow breaks, eliminates small holes and fills gaps in the contours.

THE NOVEL APPROACH FOR NOISE REMOVAL CUM EDGE DETECTION
In the proposed method, closing then followed by opening is performed using an appropriate Structuring Element (SE) on the image to be processed. Again closing operation is performed on the resultant image. This removes the noise from the image and hence is used to pre-process the image. The choosing of structuring element is a key factor in morphological image processing. The size and shape of the structuring element decide the final results of detected edges and put de-noising in both binary and gray scale images.
Three methods are proposed to detect edges in the image:

Method 1
The edge of the image can also be detected by the following process. The edge of an image J which is denoted by E (J) is defined as the difference set of the domain of J and the eroded domain of J.
It can be depicted by the following Equation 5:

Method 2
The edge of the image is detected by the following process. The edge of an image J which is denoted by E (J) is defined as the difference set of the dilation domain of J and the domain of J.
It can be depicted by the following Equation 6:

Method 3
The edge of the image can also be detected by the following process. The edge of an image J which is denoted by E (J) is defined as the difference set of the dilated domain of I and the eroded domain of J.
It can be depicted as follows Equation 7:

EXPERIMENTAL RESULTS
A possible solution for detecting cracks located on very dark image areas would be to apply the crackdetection algorithm locally on this area and select a low threshold value. For the case of the border between regions of different color, a possible solution would be to perform edge detection or segmentation on the image and confine the filling of cracks that cross edges or region borders to pixels from the corresponding region.
The proposed method are applied the 2-d digitized painting first to eroded the image, then the dilated the image, then opening and final close the image. Method 1 deals with erosion of an image, Method two deals with dilated of an image and method three opening and closing of an image. Calculate PSNR value for each step is calculated and to find the optimum structuring element is found.
The following Table 1-5 shows statistical analysis of error value comparison among the various structuring elements to find the optimal solution for choosing the structuring element.
As can be seen from Fig. 1-5, the results of the proposed method with structuring elements such as Diamond (2,3)

CONCLUSION
In this study, a novel MM based algorithm is proposed to remove the cracks in digitized paintings. The proposed method is applied to 2-d digitized painting first to erode the image, then dilated the image, then opening and finally close the image. Method 1 deals with erosion of an image, Method two deals with dilated of an image and method three opening and closing of an image. We calculate PSNR value for each step and to find the optimum structuring element .The efficiency of proposed algorithm to find edges is compared with edge detectors like SOBEL, PREWITT and CANNY by using quality assessment parameter PSNR . This can be tried to other structuring element and comparison for another error like SNR, MSSIM, RMSE can be carried out. The limitations of these for only 2Dimages and tried to other structuring element and comparison for another error like SNR, MSSIM, RMSE can be carried out.