180 International Journal for Modern Trends in Science and Technology Tamper Detection using Watermarking Scheme and K-Mean Clustering for Bio Medical Images R. Suganya 1 | Dr. R Kanagavalli 2 1,2 ISE, The Oxford College of Engineering, Bangalore, Karnataka, India. To Cite this Article R. Suganya, Dr.R Kanagavalli, DzTamper Detection using Watermarking Scheme and K-Mean Clustering for Bio Medical Imagesdz, International Journal for Modern Trends in Science and Technology, Vol. 02, Issue 11, 2016, pp. 180-185. In this paper, we focus image authentication and tamper detection using K-mean clustering based on fragile watermarking scheme. The two important aspects of the authentication watermarking scheme are Tamper detection and localization accuracy. In our scheme, clustering values of the watermarked image used as secret key. It can be detect any amendment is made to image and also point out the exact location that have been modified. Significant features of the schemes are reducing the time complexity and improving the PSNR value , with stand attacks. Original image is not required for verification. KEYWORDS: Watermarking, k- means clustering, Tamper detection. Copyright © 2016 International Journal for Modern Trends in Science and Technology All rights reserved. I. INTRODUCTION In digital media, with the fast development of the Internet, digital images are used as evidences in the news and court reports. However, using dominant image processing software tools, digital images can be simply modified without any limit. Normally these customized images can cause financial and public damages to the concerned persons. Hence the development of a reliable digital image authentication scheme is a critical problem [1]. This problem can be solved by various authentication schemes that verify the integrity and authenticity of the image content. The authentication schemes may classify in to two categories: as digital signature based schemes and digital watermark based schemes [2]. A digital signature can be either an encrypted or a signed hash value of image contents and/or image characteristics. The foremost problem of signature based schemes is that they can identify if an image has been modified, but they cannot find the regions where the image has been modified. To solve this problem, many researchers have proposed watermarking based schemes for image authentication. Digital watermarking is a technology for embedding digital data in digital content (audio, images, video…). It has initiated as a tool to enhance the security. Watermarking techniques are classified into Spatial Domain and Frequency Domain. In Spatial Domain the watermarking system directly alters the main data elements (like pixels in an image) to hide the watermark data. In Frequency Domain the watermarking system alters the frequency transforms of data elements to hide the watermark data. The watermarking properties are listed as robustness, data payload, capacity, security, computational cost.  Robustness of the watermark refers to its ability to withstand non- maliciousdistortions,  Data payload is the encoded message size of a watermarked in an image,  Capacity is the amount of watermark information in an image, ABSTRACT International Journal for Modern Trends in Science and Technology Volume: 02, Issue No: 11, November 2016 ISSN: 2455-3778 http://www.ijmtst.com