International Journal of Scientific Engineering and Technology (ISSN : 2277-1581) Volume No. 2, Issue No. 8, pp : 759-765 1 Aug. 2013 IJSET@2013 Page 759 Image Compression Using Radon Transform With DCT : Performance Analysis S. Akila Pradeep, R. Manavalan Department of Computer Science, K.S.Rangasamy College of Arts and Science Thiruchengode 637215, Tamilnadu, India. Email Id: akisaha12@gmail.com, manavalan_r@rediffmail.com Abstract - Image compression is the significant research area in the field of image processing. The Transform selection in image compression has played a vital role since the size of the resultant compressed image should be reduced in comparison with the original image. Numerous image compression standards based on Wavelet Transform have been devoted in the literature but still there exist scope of yielding better compression with high quality in image reconstruction. Existing image compression technique using DWT with Biorthogonal filtering accommodates less compression ratio with poor image quality of reconstructed image. With that concern, image compression using Radon Transform with DCT (Discrete Cosine Transform) is proposed in this paper that contribute different dimension to the image compression. The image compression using Radon Transform with DCT accords best performance whereas the image compression using DWT with Bi-orthogonal filtering performs the least. Experimental evaluation has been effectuated to arrive at the conclusion that better results for PSNR and compression ratio is used for selecting best image compression technique. Keywords - Image Compression, Discrete Wavelet Transform (DWT), Radon Transform (RT), Discrete Cosine Transform (DCT). I. INTRODUCTION With the ever growing technology, it is significant to handle vast amount of image data and needs to be stored in a proper way by exploiting efficient techniques normally succeed in compressing the images. The representation of an image by reducing the amount of data is termed as image compression. Moreover, the ultimate goal of image compression is to reduce both spatial and spectral redundancy to accumulate or transmit data in a proper manner. Once the image is compressed it needs to be reconstructed at the receiver side to reproduce the source image. In literature, numerous image compression techniques are proposed to compress the image by accomplishing better image quality. In image compression Discrete Wavelet Transform (DWT) has witnessed great success in enhancing the compressed image quality. 1-D, 2-D DWT based compression techniques are exploited for vertical and horizontal directions. In order to efficiently capture the point singularities of image, classical 2-Dim DWT are used. But, improper alignment of image in horizontal and vertical directions fails to capture the line singularities. With respect to the property of DWT, improper alignment of edges and contours create the energy of image that spreads across the sub bands. All the DWT based compression technique takes the advantage of either wavelet 9/7 filter or wavelet 5/3 filter for better image compression. The wavelet 9/7 filter is the famous Bi- orthogonal wavelet filter, which can be used as the default filter in the irreversible wavelet filter. The wavelet based Bi-orthogonal filter coefficient introduced by V. Kumar, et al. [viii] accomplish good evaluation result in terms of metrics like PSNR and MSE as compared to conventional DWT based image compression techniques namely, wavelet 9/7 filter or wavelet 5/3 filter. The existing image compression technique using DWT with bi-orthogonal filtering gives lower performance in terms of image quality metrics like PSNR. With that concern, an effective image compression technique using radon transform with DCT (Discrete Cosine Transform) is proposed. It acts as a more promising way of compressing texture images. The image compression technique DCT is integrated with Radon Transform, which is well suited for accomplishing better performance in terms of PSNR. The performance of existing image compression technique and proposed image compression method are analyzed. The rest of the paper is composed as follows: Section 2 reviews the related works of existing image compression techniques. Section 3 describes proposed work and percolates a comparative study of existing image compression technique with the proposed approach for compressing the images. Experimental analysis is discussed in section 4. Finally, section 5 sums up the paper with conclusion and further direction. II. RELATED WORKS In the field of image processing, Wavelet transform has gained increasing attention and proved to be very useful tools. Wavelets are mathematical tool for hierarchically decomposing functions.