Efficient PCA-based image compression via secure outsourcing edge cloud
Yuling Luo, Shiqi Zhang, Shunsheng Zhang, Junxiu Liu, Ce Liang, Yang Su · 2022
The increasing of image pixel size in recent years has lifted the expense for the image data storage and transmission drastically. Image compression could be one effectively solution to alleviate this difficulty. However, in some cases, the computational terminal resource is constrained and insufficient to effectively perform the image compression. An image compression based on principal component analysis (PCA) outsourcing protocol is proposed in this paper to handle such problems. The abundant computing resources of the edge cloud are used to perform the image compression effectively that the terminal cannot. The image is encrypted and sent to the cloud by terminal. The encrypted matrix is directly calculated by the cloud and the computational result is returned to the terminal. After the result is received by the terminal, the correctness of the result is verified. The result will be decrypted if it passed the verification. Otherwise, the result is returned to the edge cloud for recalculation. According to a series of comprehensive performance analysis, the proposed protocol can substantially improve the efficiency of local computation, also guarantee the privacy of the terminal and correctness of the results.