Differential Privacy Protection of Face Images Based on Region Growing

Face images, as an information carrier, are rich in sensitive information. Direct publication of these images would cause privacy leak, due to their natural weak privacy. Most of the existing privacy protection methods for face images adopt data publication under a non-interactive framework. However, the E-effect under this framework covers the entire image, such that the noise influence is uniform across the image. To solve the problem, this paper proposes region growing publication (RGP), an algorithm for the interactive publication of face images under differential privacy. This innovative algorithm combines the region growing technique with differential privacy technique. The privacy budget E is dynamically allocated, and the Laplace noise is added, according to the similarity between adjacent sub-images. To measure this similarity more effectively, the fusion similarity measurement mechanism (FSMM) was designed, which better adapts to the intrinsic attributes of images. Different from traditional region growing rules, the FSMM fully considers various attributes of images, including brightness, contrast, structure, color, texture, and spatial distribution. To further enhance algorithm feasibility, RGP was extended to atypical region growing publication (ARGP). While RGP limits the region growing direction between adjacent sub-images, ARGP searches for the qualified sub-images across the image, with the aid of the exponential mechanism, thereby expanding the region merging scope of the seed point. The results show that our algorithm can satisfy E-differential privacy, and the denoised image still have a high availability.

An Effective Multi-Task Two-Stage Network with the Cross-Scale Training Strategy for Multi-Scale Image Super Resolution

Convolutional neural networks and the per-pixel loss function have shown their potential to be the best combination for super-resolving severely degraded images. However, there are still challenges, such as the massive number of parameters requiring prohibitive memory and vast computing and storage resources as well as time-consuming training and testing. What is more, the per-pixel loss measured by L2 and the Peak Signal-to-Noise Ratio do not correlate well with human perception of image quality, since L2 simply does not capture the intricate characteristics of human visual systems. To address these issues, we propose an effective two-stage hourglass network with multi-task co-optimization, which enables the entire network to focus on training and testing time and inherent image patterns such as local luminance, contrast, structure and data distribution. Moreover, to avoid overwhelming memory overheads, our model is capable of performing real-time single image multi-scale super-resolution, so it is memory-friendly, meaning that memory space is utilized efficiently. In addition, in order to best use the underlying structure and perception of image quality and the intermediate estimates during the inference process, we introduce a cross-scale training strategy with 2×, 3× and 4× image super-resolution. This effective multi-task two-stage network with the cross-scale strategy for multi-scale image super-resolution is named EMTCM. Quantitative and qualitative experiment results show that the proposed EMTCM network outperforms state-of-the-art methods in recovering high-quality images.

INVESTIGATION OF THE METHOD OF DIRECT LASER WRITING OF OPTICAL ELEMENTS WITH BINARY HIGH-CONTRAST AMPLITUDE-PHASE TRANSMISSION

A method is proposed for formation on one substrate of two superimposed optical structures - a binary phase structure and an analog high-contrast amplitude structure made on a thick chromium film in the form of a regular two-dimensional zero-order diffraction grating with a variable fill-factor of cells. A numerical and experimental study of this method is carried out as applied to an optical transparency for generating the structure of a gamma-coupled laser beam. The quality of a high-contrast structure, suitable for practical application, was experimentally achieved, with an optical density of a chromium film of about 4.3, when measured at a wavelength of 532 nm, and with a minimum size of transparent and opaque windows of the order of 1x1 μm. This method can be used to synthesize amplitude-phase transparencies with a large alternating range of change in the amplitude optical transmittance, with a relatively slow (smooth) change in the transmittance (with the carrier spatial frequency of the amplitude modulation determined by the period of the above two-dimensional zero-order diffraction grating).

The step-type contrast structure for a second order semi-linear singularly perturbed differential-difference equation

The step-type contrast structure for a second order semi-linear singularly perturbed differential-difference equation is studied. Using the methods of boundary function and fractional steps, we construct the formula asymptotic expansion of the problem. At the same time, based on sewing techniques, the existence of the step-type contrast structure solution and the uniform validity of the asymptotic expansion are proved.