Detection of medical identity theft in medical images through digital watermarking /

The risk of medical identity theft is increased rapidly due to the advancement in technology. Accordingly, the healthcare system security and privacy becomes an important issue. This is because any alteration to medical information may cause a devastating effect to the patient. In this work, a digit...

全面介紹

Saved in:
書目詳細資料
主要作者: Yahuza, Muktar
格式: Thesis
語言:English
出版: Kuala Lumpur : Kulliyyah of Engineering, International Islamic University Malaysia, 2015
主題:
在線閱讀:http://studentrepo.iium.edu.my/handle/123456789/4529
標簽: 添加標簽
沒有標簽, 成為第一個標記此記錄!
LEADER 028910000a22002770004500
008 150216t2015 my a g m 000 0 eng d
040 |a UIAM  |b eng 
041 |a eng 
043 |a a-my--- 
050 0 0 |a R858 
100 1 |a Yahuza, Muktar 
245 1 |a Detection of medical identity theft in medical images through digital watermarking /  |c by Muktar Yahuza 
260 |a Kuala Lumpur :   |b Kulliyyah of Engineering, International Islamic University Malaysia,   |c 2015 
300 |a xv, 88 leaves :  |b ill. ;  |c 30cm. 
502 |a Thesis (MSCIE)--International Islamic University Malaysia, 2015. 
504 |a Includes bibliographical references (leaves 74-79) 
520 |a The risk of medical identity theft is increased rapidly due to the advancement in technology. Accordingly, the healthcare system security and privacy becomes an important issue. This is because any alteration to medical information may cause a devastating effect to the patient. In this work, a digital watermarking that detects any attempt of altering patient data is proposed. The discrete wavelet transform of the 8 x 8 non-overlapping blocks of the medical test image is generated prior to the embedding process. A 64-bits binary equivalent of digit numbers representing patient's entry date and file ID used as the watermark is embedded inside the corresponding patient's medical image by quantizing the coefficient of the highest frequency components of each block. After the medical image is transferred to its destination, the watermark is extracted and compared to the original watermark for authentication. The average value of the peak signal to noise ratio performance metric shows that the level of imperceptibility of the technique, was found to be 82.88 dB, and also the average values of the mean square error, and that of structural similarity showed that the level of distortion of the watermarked image was found to be 7.9e-4 and 0.9112 respectively. A number of attacks which include JPEG compression, Filtration, Gaussian noise, Salt and pepper noise, and contrast enhancement were applied to the watermarked image. The proposed algorithm enables quick and excellent detection capability of any modification done to the medical image. 
596 |a 1 
655 7 |a Theses, IIUM local 
690 |a Dissertations, Academic  |x Department of Electrical and Computer Engineering  |z IIUM 
710 2 |a International Islamic University Malaysia.  |b Department of Electrical and Computer Engineering 
856 4 |u http://studentrepo.iium.edu.my/handle/123456789/4529 
900 |a sbh-ls 
999 |c 437450  |d 467291 
952 |0 0  |6 T R 000858 Y13D 2015  |7 0  |8 THESES  |9 760220  |a IIUM  |b IIUM  |c MULTIMEDIA  |g 0.00  |o t R 858 Y13D 2015  |p 11100339377  |r 2017-10-20  |t 1  |v 0.00  |y THESIS 
952 |0 0  |6 TS CDF R 858 Y13D 2015  |7 0  |8 THESES  |9 853157  |a IIUM  |b IIUM  |c MULTIMEDIA  |g 0.00  |o ts cdf R 858 Y13D 2015  |p 11100339378  |r 2017-10-26  |t 1  |v 0.00  |y THESISDIG