Compression Technique Using Different Dr. Vineet Richariya Mrs. Shweta Shrivastava Naman Agrawal Professor Assistant Professor Research Scholar Dept. of Comp. Science & Engg. Dept. of Comp. Science & Engg. M.Tech Comp. Science & Engg. L.N.C.T Bhopal (M.P), India L.N.C.T Bhopal (M.P), India L.N.C.T Bhopal (M.P), India vineetrich100@gmail.com shwetashri.26@gmail.com namanagrawal2003@gmail.com Abstract- With the development of Digital image processing technolo there are several applications. One of the applications is an image compression. The paper assigned a comparative study has been done using different wavelet function such as Haar, db4 and db6 for the compression and reconstruction of the image using MATLAB and determine the PSNR, Entropy, Ener and compression ratio of the image. For efficient representation of digital image in order to reduce the memory required for storage, improve the data access rate from storage device and reduce the bandwidth and time required for data transfer across communication channel wavelet transform is the best solution. Motivation of the analysis is to encourage the amateur researcher in the field of image compression, so that they can understand easily the concept of image compression and can contribute in developing more efficient compression algorithm. This will benefit interested researchers to carry out further work in this thrust area of research. Keywords: compression, wavelet transform, PSNR. Quantization, Entropy coding, Ener. I. INTRODUCTION The term digital image processing generally refer to processing of a two dimensional image by a digital computer. A digital image is an array of real or complex number represented by a finite number of bits used for digital image processing and in this finite number of elements, each of which has a particular location and value. These elements are referred to as picture elements, image elements, pels, and pixels. Pixel is the term most widely used to denote the elements of a digital image. An image may be defined as a twodimensional function f(x, y) where x and y are spatial (plane) coordinates and the amplitude of f at any pair of coordinates (x, y) is ca lled the intensity or gray level of the image at that point. When x, y and the amplitude values of f are all finite discrete quantities the image is called digital image. This paper is organized as follows: Section I describes the concept of a image compression in brief with its elements. Section II presents a survey of several proposed concepts in image compression. Section III provides an Compression technique based on wavelet transform. an analysis and a parameter wise comparison and simulation result among all the surveyed papers. Section IV presents an analysis and result. Section V conclusion of this paper and future work and lastly the references. II. LITERATURE SURVEY Following references are used for details regarding Digital image compression based encoding and decoding and algorithm for the paper work: compression using wavelets and JPEG2000: [1] have to introduce the DWT, to illustrate its link with filters and filter banks and to illustrate how it may be used as part of an image coding algorithm. It concludes with a look at the qualitative differences between images coded using JPEG 2OOO and those coded using the existing JPEG standard. The JPEG2000 Still Coding System: An Overview [2], have provide information of still image encoding, new standard, the JPEG2000. This paper tells the advantages of JPEG 2000 which is a rate-distortion and subjective image quality performance are superior to existing other standards and lossless and lossy compression, embedded lossy to lossless coding, progressive transmission by pixel accuracy and by resolution, robustness to the www.ijrcct.org Page 617
presence of bit-errors and region-of-interest coding, are some representative features of JPEG 2000. Compression with Different Types of s, [3] In this paper, different wavelets have been used to perform the transform of a test image and their results have been discussed and analyzed. The analysis has been carried out in terms of PSNR (peak signal to noise ratio) obtained and time taken for decomposition and reconstruction. This analysis will help in choosing the wavelet for decomposition of images as per their application. III. IMAGE COMPRESSION BASED ON WAVELET TRANSFORM compression addresses the problem of reducing the amount of data required to represent a digital image. It is a process intended to yield a compact representation of an image, thereby reducing the image storage/transmission requirements. The transform of a signal is just another form of representing the signal. It does not change the information content present in the signal. The Transform provides a time-frequency representation of the signal. It was developed to overcome the short coming of the Short Time Fourier Transform (STFT), which can also be used to analyze non-stationary signals. While STFT gives a constant resolution at all frequencies, the Transform uses multi-resolution technique by which different frequencies are analyzed with different resolutions. Fig. 2 transform B. Quantization Quantization, involved in image processing, is a lossy compression technique achieved by compressing a range of values to a single quantum value. When the number of discrete symbols in a given stream is reduced, the stream becomes more compressible. For example, reducing the number of colors required to represent a digital image makes it possible to reduce its file size. Specific applications include DCT data quantization in JPEG and DWT data quantization in JPEG 2000. C. Entropy Coding After the data has been quantized into a finite set of values, it can be encoded using an Entropy Coder to give additional compression. By entropy, mean the amount of information present in the data, and an entropy coder encodes the given set of symbols with the minimum number of bits required to represent them. IV. IMPLEMENTATION AND RESULT Fig. 1. Flow chart for image compression A. Transform The basic procedure followed is after the reading image, wavelet transform is applied to get wavelet coefficient, which are quantized. The quantized coefficients are encoded. Then the decoding is done and inverse quantization is carried out on the compressed coefficient and in the next step inverse wavelet transform is done to get the compressed image. www.ijrcct.org Page 618
To evaluate the performance of the whole process the following performance parameter are evaluated: Fig. 5. 2 nd Level Haar Transform and Transform image i. PSNR. ii. Ener. iii. Compression ratio. iv. Entropy. Fig..6 3 rd Level Haar Transform and Transform image (CR=20:1) The transform is based on three wavelet function. i. Haar. ii. Duabechies 4 (db4). iii. Duabenchies 6 (db6). A. transform using haar function and corresponding image with compression ratio A=imread (lena.jpg) W N = haar (N); W M = haar (N); Subplot (1, 2, 1), imshow (B); B. s transform using duabechies (db4) function and corresponding image with compression ratio A= imread (lena.jpg) W N = db4 (N); W M = db4(n); subplot (1, 2, 1), imshow (B); Fig..7 Original Lena image (lena.jpg) Fig. 3. Original Lena image(lena.jpg) Fig. 4. 1 st Level Haar Transform and Transform image Fig. 8. 1 st Level db4 Transform and Transform image Fig. 9. 2 nd Level db4 Transform and Transform image www.ijrcct.org Page 619
Fig. 10.3. rd Level db4 Transform and Transform image (CR=20:1). C. transform using duabechies (db6) function and corresponding image with compression ratio A=imread (lena.jpg) W N = db6 (N); W M = db6 (N); subplot (1, 2, 1), imshow (B); Fig. 14. 3 rd Level db6 Transform and Transform image (CR=20:1) D. Quality Measurment Qualities of the transform image are measured by PSNR, Ener and Compression ratio. TABLE I PSNR VALUE FOR DIFFERENT WAVELET FUCTION WITH COMPRESSION RATIO 25:1 Lena.jpg (CR 20:1) 53.0805 db 61.2646 db 53.0750 db Fig. 11. Original Lena image (lena.jpg) TABLE II PSNR VALUE OF RADAR IMAGE FOR DIFFERENT WAVELET FUCTION WITH COMPRESSION RATIO 25:1 Fig.12. 1 st Level db6 Transform and Transform image FAA_radar.jpg (CR 25:1) SCR_radar.jpg (CR 25:1) Space radar.jpg (CR 20:1) 53.6480 db 55.6629 db 53.7033 db 54.7653 db 56.7450 db 54.7668 db 58.7818 db 60.2016 db 58.7817 db TABLE III Fig. 13. 2 nd Level db6 Transform and Transform image ENERGY OF THE TRANSFORM RADAR IMAGE FOR DIFFERENT WAVELET FUCTION WITH COMPRESSION RATIO 25:1 (Total Ener) Ener % Ener % Ener % www.ijrcct.org Page 620
FAA_radar. jpg (7.0099 x (25:1) SCR_radar.j pg (1.1989x (25:1) Space radar.jpg (1.4450 x (20:1) 6.8942 x 98.35 6.9216 10 4 x 10 4 98.74 1.1842 x 10 4 98.78 1.4272x 10 4 98.77 TABLE IV 1.1890 x 10 4 99.18 1.4340 x 10 4 99.24 6.9005x 10 4 98.44 1.1855 x 10 4 98.89 1.4291 x 10 4 98.90 ENERGY OF THE TRANSFORM IMAGE FOR DIFFERENT WAVELET FUCTION WITH COMPRESSION RATIO 25:1 (Total Ener) Ener % Ener % Ener % Improve the data access rate. REFERENCES [1] S. Lawson and J. Zhu. compression using wavelets and JPEG2000: a tutorial, IEEE, Electronics & Communication Engineering Journals,(2000) [2] Charilaos Christopoulos, Athanassios Skodras and Touradj Ebrahimi. The JPEG2000 Still Coding System: An Overview, Published in IEEE Transactions on Consumer Electronics, Vol. 46, No. 4, (2000), 1103-1127. [3] Javed Akhtar, Dr Muhammad Younus Javed. Compression with Different Types of s, IEEE 2nd International Conference on Emerging Technologies Peshawar, Pakistan,(2006), 13-14. [4] Rafael C. Gonzalez, Richard E. Woods. Digital Processing, second edition, Pearson Education.(2002). [5] Anil K. Jain. Fundamentals of Digital Processing, Prentice Hall Information & System Sciences Series, (2001). [6] Martin, Vetterli & Jelena Kovacevic. s and Subband Coding, Prentice Hall PTR,(1995). [7] Patrick J. Van Fleet. Discrete Transformations: an Elementary Approach with Applications, (1962). [8] Michel Misiti, Yves Misiti. Toolbox 4 User s Guide, The Math Works and Inc, (2008). 1. Lena.jpg (5.0811 x 5.018 8 x 10 4 98.77 5.047 6 x 10 4 99.34 5.030 98. 0 x 10 4 99 TABLE V ENTROPY OF THE IMAGE IMAGE NAME ENTROPY Lena.jpg 0.0938 V. CONCLUSION AND FUTURE WORK Based on the results obtained the conclusion is that, daubenchies4 is the good wavelet function as compare to haar and duabenchies6. Daubenchies4 gave the good quality of image and PSNR value for different compression ratio. Some salient features of image compression can be summarized as: Reduction of memory requirement for storage. Reduction of Bandwidth and time requirement for data transfer in communication channel. www.ijrcct.org Page 621