International Journal of Innovative Research in Science, Engineering and Technology

International Journal of Innovative Research in Science, Engineering and Technology

Menu

ISSN ONLINE(2319-8753)PRINT(2347-6710)

All submissions of the EM system will be redirected to Online Manuscript Submission System. Authors are requested to submit articles directly to Online Manuscript Submission System of respective journal.

Comparative Analysis of Interpolation and Texture Synthesis Method for Enhancing Image

Parth Bhatt1, Prof. Sachin Patel2, Prof. Rakesh Pandit3
 I.T Department, PCST, Indore, Madhya Pradesh, India1, HOD, I.T Department, PCST, Indore, Madhya Pradesh, India2 Assistant Professor, I.T Department, PCST, Indore, Madhya Pradesh, India3
Related article at Pubmed, Scholar Google

Visit for more related articles at International Journal of Innovative Research in Science, Engineering and Technology

International Journal of Innovative Research in Science, Engineering and Technology

Abstract

Interpolation is the method of enlarging or stretching an image from a smaller original image to a larger resultant image. Whereas, Texture synthesis is the method of cleaning the image by using patches or pixels for making the image resolution higher and better than the original image. Here in this paper we have given an overview of different Interpolation and Texture Synthesis Methods. We have reviewed various Interpolation Algorithms for enlarging the image. Also, we have reviewed different Texture Synthesis methods for making the image resolution better and finer.

Keywords
Interpolation, Texture Synthesis, Image Enhancement, DWT

INTRODUCTION
An image Interpolation is the method of enlarging the smaller low resolution image to a larger high resolution image which can be defined as Image Scaling. Whereas, approximating the value of continues function by using discrete samples is also defined as an Interpolation [16]. Nowadays, Image interpolation is also available in many image processing tools like Photoshop [1]. Also ithas many applications like digital photograph, remote sensing, medical imaging, image decomposition, to correct spatial distortion and many more. We have shown the basic concept of image enlargement using Interpolation in figure 1.
The digital image is a signal which mainly varies in two dimensions. This signal is sampled and quantized to get values. All these values are called the pixels of an image. While increasing the resolution of an image from low to high, it is called up-sampling or up-scaling whereas, the reverse is called down sampling or down scaling [22]. Here, in this paper we have mainly focused on upsampling only. Primarily, there are two main categories for interpolation: Adaptive and Non-Adaptive. We have shown the comparisons of both the categories.
The process of constructing a large digital image from a small digital sample image algorithmically is known as Texture Synthesis. Basically, Texture synthesis is used to create large non-repetitive background images and expand small pictures by removing noise and also to fill in holes in images. The Primary goal of a Texture Synthesis process is to synthesize a new texture in such a way that when it is been perceived by some human observer, it appears to be generated by same underlying process.
Basically, two methods are used for cleaning gray scale images: Pixel Based Texture Synthesis and Patch Based Texture Synthesis. Whereas Segmentation (object select by boundary) and selecting area (select image area) are used for cleaning the Color images (RGB image) [20]. Also, noise can be removed by taking different size and shapes of patch and then using both methods. Peak Signal to Noise Ratio (PSNR) is used as a measure of quality.
We have organized our paper in a following manner. Section II gives an overview of Image Interpolation using Adaptive and Non-Adaptive method. Section III describes the method for Enhancing and cleaning the image using Texture Synthesis Method. Section IV shows the comparison for the methods of Interpolation and Texture Synthesis. Section V concludes the paper.

II. INTERPOLATION
Interpolation is the process of transferring image from one resolution to another without losing image quality. In Image processing field, image interpolation is very important function for doing zooming, enhancement of image, resizing any many more. Here we have categorized Interpolation into two: Non-Adaptive Interpolation and Adaptive Interpolation.
A. Non-Adaptive Interpolation
• Nearest Neighbour Interpolation: This method uses nearest neighbour’s pixel to fill interpolated points and so it is considered to be very simple and requires less computation. In this method the available values are just copied, not the interpolated values as it do not change the values.
• Bilinear Interpolation: The interpolated point is filled with four closest pixel’s weighted average in this method. Here in this method we perform two linear interpolations, in horizontal direction and then linear interpolation in vertical direction. In Bilinear Interpolation method we calculate four interpolation functions for grid point.
• Bicubic Interpolation: The interpolated point is filled with sixteen closest pixel’s weighted average in Bicubic Interpolation. Because of these, we get a sharper image than Bilinear Image. The comparison between the three Non-Adaptive Interpolation methods is shown below in figure 2.
B. Adaptive Interpolation
• Threshold Based Interpolation: In this method, more pixel values are considered while calculating interpolated point’s value as well as the noise present in image. Here instead of finding mean value of pixels, we can use max or median function of matlab as per the type of image [11]. Example is shown in figure 3.
• Edge Guided Interpolation: In an Edge-Guided Image Interpolation method we used Directional Filtering and Data Fusion presented in [5]. Here we partition pixels into two directional and orthogonal subsets for the edge information. Directional interpolation is made for each Subset and two interpolated values are fused. The algorithm presented till now works for gray scale images only. Here we have presented the algorithm that works for RGB image also. Each R, G and B components of one image are stored into three different images of two dimensions and give that as a input to original algorithm. Finally all the three output arrays are merged into single RGB image [4].
• DWT Based Interpolation: We have studied “image up-sampling using DWT presented in [9]. Here they have used 9/7 bi-orthogonal spline based DWT. The Presented figure shown below preserves the edges and colour of original image. Below we have shown the figure 5, how the image up-sampling is done where S is scaling factor and I is original image [22].
Mapping of an image onto the object surface either synthetic or digitized, then such a technique is called texture mapping [17][18].The mapped image, usually rectangular, is called a texture map or texture [4]. A texture can be used to modulate various surface properties, including color, reflection, transparency, or displacements. In the field of computer graphics the content of a texture can be very general in mapping a color texture patterns. Texture can be referred as visual or tactile surfaces composed of repeating patterns, such as a fabric.
Texture synthesis is the process of algorithmically constructing a large digital image from a small digital sample image by taking advantage of its structural content. Texture synthesis can be used to fill holes in images, create large non-repetitive background images and expand small pictures [17]. Here we have categorized the method of Texture Synthesis into two: Pixel Based Texture Synthesis and Patch Based Texture Synthesis.
A. Pixel Based Texture Synthesis
Pixel-based texture synthesis method is based on a non- parametric sampling method. It also assumes that a pixel value at a certain location only depends on its immediate neighbourhood [19]. When choosing the value of the next pixel in the output image the method uses the populated portion of the pixels neighbourhood to exhaustively search for the best matched region in the sample image [21].
B. Patch Based Texture Synthesis
The method synthesizes a new image by stitching together small patches from the sample image. In this method synthesizes a resultant image is generated block by block in raster order. Square blocks are used to capture the primary pattern in the sample texture. A block is randomly selected from the sample image and pasted into the new image beginning at the first row and the first column. Then another block is selected as a candidate neighbour. It is placed next to the first block so that they overlap one another [21].
We have used matlab for showing the comparison between different Interpolation methods. Experiments have been done on LINA images of the size 256 x 256. We have used Pick Signal to Noise Ratio (PSNR) for comparison of all algorithms. Visual quality is the most important parameter for the effectiveness. We have shown all the comparisons in the below table 1. The PSNR is defined as: PSNR = 20 · log 10(MAX i / √MSE).

V. CONCLUSION
In this paper we have shown the comparative analysis of different interpolation and texture synthesis methods. We have also shown the comparison of different Interpolation methods. For various purposes adaptive methods are better and for generalized tools, non-adaptive methods are good. For image up sampling interpolation method is very good. In future we would like to modify above methods so as to make it work better.

ACKNOWLEDGMENT
We extend our sincere acknowledgements to all the faculty members of our institutes and other contributors for providing us the technical assistance for carrying out the study. Our truthful appreciation is to all the persons who were there to provide the facilities and help us for preparing this research paper.

Tables at a glance
Table icon
Table 1
 

Figures at a glance
Figure 1 Figure 2 Figure 3 Figure 4
Figure 1 Figure 2 Figure 3 Figure 4
Figure 5 Figure 6 Figure 7 Figure 8
Figure 5 Figure 6 Figure 7 Figure 8
 

References
  1. Adobe® CS2 software. (http://www.adobe.com/products/photoshop/)
  2. D. Kirk, Graphics Gems III (IBM Version), Academic Press, San Diego, CA, 1992.
  3. G. Sharma and H.J. Trussell, Digital Color Imaging, IEEE Transactions on Image Processing, 6 (7) (1997) 901-932.
  4. Image Types :: Displaying Bit-Mapped Images : (MATLAB®), http://www.mathworks.in/help/techdoc/creating_plots/f2-10709.html
  5. Lei Zhang, Xiaolin Wu, “An Edge-Guided Image Interpolation Algorithm via Directional Filtering and Data Fusion”, IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL. 15, NO. 8, AUGUST 2006.
  6. Liyakathunisa & C.N. Ravi Kumar, "A Novel and Efficient Lifting Scheme based Super Resolution Reconstruction for Early Detection of Cancer in Low Resolution Mammogram Images", International Journal of Biometrics and Bioinformatics (IJBB), Volume (5) : Issue (2) : 2011.
  7. M.D. Fairchild, Color Appearance Models, Reading, MA: Addison Wesley, 1997.
  8. P. Thevenaz, T. Blu and M. Unser, “Image Interpolation and Resampling,” Handbook of Medical Imaging, Processing and Analysis, pp. 393-420,2000.
  9. Ping-Sing Tsai, Tinku Acharya,” Image Up-Sampling Using Discrete Wavelet Transform”, 9th JCIS 2006, 8 to 11 October 2006.
  10. Recommendations on Uniform Color Spaces, Color Difference Equations, Psychometric Color Terms, C.I.E, Supplement no. 2 to CIE publication no. 15(E.-l 31) 1971/(TC-1.3), 1978.
  11. sapan Naik, Viral Borisagar, " Super-Resolution using Interpolation and Wavelet lifting scheme" , IJCA journals, VOL 40, 2012.
  12. Sapan Naik, Viral Borisagar," A novel Super Resolution Algorithm using Interpolation and LWT based denoising method ", IJIP journal, VOL. 6,issue 4,2012.
  13. T. Acharya and A. K. Ray, Image Processing: Principles and Applications, John Wiley & Sons, Inc., Hoboken, NJ, 2005.
  14. T. Lehmann, C. Gonner, and K. Spetzer, “Survey: Interpolation Methods in Medical Image Processing,” IEEE Trans. Med. Imaging, 18:1049-1067,1999.
  15. www.mathwork.com
  16. www.wikipedia.com
  17. J. F. Blinn and M. E. Newell. Texture and reection in computer generated images. Communications of the ACM, (19):542546, 1976.
  18. E. Catmull. A Subdivision Algorithm for Computer Display of Curved Surfaces. Phd thesis, Computer Science Department, University of Utal,, Salt Lake City, Utah, 1974.
  19. D. Scharstein. Synthesis Algorithm, volume 1583/1999 of Lecture Notes in Computer Science. Springer Berlin / Heidelberg, 1999.
  20. Image Enhancement Techniques byTexture Synthesis by Ankit Shah, Parth Bhatt, Prof. Kirit J.Modi, IJETAE - International Journal of Emerging Technology and Advanced Engineering (ISSN 2250-2459, Volume 2, Issue 1, January 2012)
  21. Real Time Image Enhancement Using Texture Synthesis (RETS) by Parth Bhatt, Ankit Shah, Sunil Pathak, ISSN: 2277-3754 International Journal of Engineering and InnovativeTechnology (IJEIT) Volume 1, Issue 3, March 2012
  22. Image Enhancement Using Various Interpolation Methods by Parth Bhatt, Sachin Patel, Ankit Shah, Sanjay Patel, IRACST - International Journal of Computer Science and Information Technology & Security (IJCSITS), ISSN: 2249-9555 Vol. 2, No.4, August 2012