DocumentCode :
2492477
Title :
A fragile invertible watermarking technique for the authentication of medical images
Author :
Al-Gindy, A.
Author_Institution :
Coll. of Eng., Ajman Univ. of Sci. & Technol., Ajman, United Arab Emirates
fYear :
2010
fDate :
15-18 Dec. 2010
Firstpage :
191
Lastpage :
195
Abstract :
This paper deals with a fragile watermarking technique for the authentication of medical images. Medical images are stored in archiving and communication systems that are accessed by the radiologists for diagnosis. The proposed method insure the integrity of the medical image data that is being transferred over public network. Any modification to the watermarked image can be detected using the proposed watermarking method. A unique 14 decimal digits number (signature) representing patient´s entry date and file ID embedded inside the patient´s medical image in an imperceptible way without increasing the data size that need to be transferred. This signature can be extracted at the radiologist viewer work stations and used for the authentication while the modified data is restored back to original if the image found to be authentic. This kind of erasable embedding process would ensure medical image retrieval without any modification to the image data after the authentication process. The proposed frequency domain watermarking method go along with the unique need of medical images for diagnosis.
Keywords :
authorisation; feature extraction; image coding; image restoration; image retrieval; image watermarking; medical image processing; archiving system; communication system; decimal digit number; erasable embedding process; file ID; fragile invertible watermarking technique; frequency domain watermarking method; image restoration; medical image authentication; medical image retrieval; patient entry date; public network; radiologist; signature extraction; Artificial neural networks; Biomedical imaging; Cryptography; Discrete cosine transforms; Head; Image restoration; Watermarking; DCT; medical images; watermarking;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Signal Processing and Information Technology (ISSPIT), 2010 IEEE International Symposium on
Conference_Location :
Luxor
Print_ISBN :
978-1-4244-9992-2
Type :
conf
DOI :
10.1109/ISSPIT.2010.5711776
Filename :
5711776
Link To Document :
بازگشت