当前位置: X-MOL 学术Multimedia Syst. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Medical image encryption and compression by adaptive sigma filterized synorr certificateless signcryptive Levenshtein entropy-coding-based deep neural learning
Multimedia Systems ( IF 3.5 ) Pub Date : 2021-04-10 , DOI: 10.1007/s00530-021-00764-y
C. Thirumarai Selvi , J. Amudha , R. Sudhakar

Pre-processing of medical images plays a vibrant part in the field of medicine to detect patient’s disease at an earlier stage. Hospitals and medical centers generate an enormous volume of digital medical images day by day, which is used for several purposes of diagnostic procedures. Because of many images,for secured transmission, image compression is required to reduce the redundancies in the image and to accomplish the proficient image communication. To reduce the redundancies in the image and to accomplish the proficient communication of images. A competent Adaptive sigma filterized synorr certificateless signcryptive Levenshtein entropy coding-based deep neural learning (ASFSCSLEC-DNL) technique is presented to develop the image encryption and compression. The main goal of the ASFSCSLEC-DNL technique was to improve the security level of medical image transmission. The deep feed-forward artificial neural network was applied in the ASFSCSLEC-DNL technique for medical image pre-processing, encryption, and compression with multiple layers. The adaptive sigma filter was employed to denoise the medical image. The medical image encryption and signature generation were done with synorr certificateless signcryption. Finally, Levenshtein entropy encoding was applied to compress images. Then the compressed image was sent to the receiver where the decompression and decryption are implemented using Levenshtein entropy decoding and synorr certificateless decryption. Investigational estimation was carried out in chest X-ray medical images and the results of ASFSCSLEC-DNL technique proved more capable in terms of higher peak signal to noise ratio and compression ratio with lesser encryption time compared to the existing state-of-the-art methods.



中文翻译:

基于自适应sigma滤波的synorr无证书签密Levenshtein熵编码的深度神经学习对医学图像进行加密和压缩

医学图像的预处理在医学领域中起着生机勃勃的作用,以便在早期发现患者的疾病。医院和医疗中心每天都在生成大量的数字医学图像,这些图像可用于多种诊断程序。由于有许多图像,为了确保传输的安全性,需要进行图像压缩以减少图像中的冗余并完成熟练的图像通信。减少图像中的冗余并完成图像的熟练沟通。提出了一种能胜任的自适应sigma滤波synorr无证书签密Levenshtein熵编码基于深度神经学习(ASFSCSLEC-DNL)技术来开发图像加密和压缩。ASFSCSLEC-DNL技术的主要目标是提高医学图像传输的安全级别。在ASFSCSLEC-DNL技术中,将深层前馈人工神经网络应用于医学图像的预处理,加密和多层压缩。使用自适应sigma滤波器对医学图像进行降噪。医学图像加密和签名生成是通过synorr无证书签名加密完成的。最后,将Levenshtein熵编码应用于图像压缩。然后将压缩的图像发送到接收器,在接收器中使用Levenshtein熵解码和synorr无证书解密实现解压缩和解密。

更新日期:2021-04-11
down
wechat
bug