Lossy image compression algorithms are pervasively used to reduce the size of
images transmitted over the web and recorded on data storage media. However, we
pay for their high compression rate with visual artifacts degrading the user
experience. Deep convolutional neural networks have become a widespread tool to
address high-level computer vision tasks very successfully. Recently, they have
found their way into the areas of low-level computer vision and image
processing to solve regression problems mostly with relatively shallow
networks.
We present a novel 12-layer deep convolutional network for image compression
artifact suppression with hierarchical skip connections and a multi-scale loss
function. We achieve a boost of up to 1.79 dB in PSNR over ordinary JPEG and an
improvement of up to 0.36 dB over the best previous ConvNet result. We show
that a network trained for a specific quality factor (QF) is resilient to the
QF used to compress the input image - a single network trained for QF 60
provides a PSNR gain of more than 1.5 dB over the wide QF range from 40 to 76.

本研究提出了一种新型的 12 层深度卷积神经网络，用于图像压缩伪影抑制，其具有分层跳过连接和多尺度损失函数。相较于普通的 JPEG，可提高高达 1.79 dB 的峰值信噪比，并且相较于先前最佳 ConvNet 结果提高高达 0.36 dB。该研究表明，训练用于特定质量因子 (QF) 的网络对于压缩输入图像所使用的 QF 是有韧性的，单个针对 QF 60 训练的网络在多种 QF 范围内 (40 至 76) 提供超过 1.5 dB 的 PSNR 增益。

CAS-CNN：一种深度卷积神经网络用于图像压缩伪影抑制

CAS-CNN: A Deep Convolutional Neural Network for Image Compression  Artifact Suppression

In this paper, we propose a new super resolution technique based on the
interpolation followed by registering them using iterative back projection
(IBP). Low resolution images are being interpolated and then the interpolated
images are being registered in order to generate a sharper high resolution
image. The proposed technique has been tested on Lena, Elaine, Pepper, and
Baboon. The quantitative peak signal-to-noise ratio (PSNR) and structural
similarity index (SSIM) results as well as the visual results show the
superiority of the proposed technique over the conventional and state-of-art
image super resolution techniques. For Lena's image, the PSNR is 6.52 dB higher
than the bicubic interpolation.

本文提出了一种基于插值和迭代反向投影（IBP）的新型超分辨率技术，通过插值和注册低分辨率图像来生成更清晰的高分辨率图像，并针对 Lena、Elaine、Pepper 和 Baboon 进行了测试，结果显示该技术优于传统和最先进的图像超分辨率技术，Lena 图像的 PSNR 比双三次插值高 6.52 dB。

使用插值后迭代反投影提高图像分辨率

Image Resolution Enhancement by Using Interpolation Followed by  Iterative Back Projection

The square and rectangular shape of the pixels in the digital images for
sensing and display purposes introduces several inaccuracies in the
representation of digital images. The major disadvantage of square pixel shapes
is the inability to accurately capture and display the details in the objects
having variable orientations to edges, shapes and regions. This effect can be
observed by the inaccurate representation of diagonal edges in low resolution
square pixel images. This paper explores a less investigated idea of using
variable shaped pixels for improving visual quality of image scans without
increasing the square pixel resolution. The proposed adaptive filtering
technique reports an improvement in image PSNR.

本文探讨使用可变形状像素来提高图像扫描的视觉质量的 less-investigated 想法，提出了一种自适应滤波技术，报告了图像 PSNR 的改进。

自适应数字扫描可变像素

Adaptive Digital Scan Variable Pixels

In this paper, we introduce a new digital watermarking algorithm using least
significant bit (LSB). LSB is used because of its little effect on the image.
This new algorithm is using LSB by inversing the binary values of the watermark
text and shifting the watermark according to the odd or even number of pixel
coordinates of image before embedding the watermark. The proposed algorithm is
flexible depending on the length of the watermark text. If the length of the
watermark text is more than ((MxN)/8)-2 the proposed algorithm will also embed
the extra of the watermark text in the second LSB. We compare our proposed
algorithm with the 1-LSB algorithm and Lee's algorithm using Peak
signal-to-noise ratio (PSNR). This new algorithm improved its quality of the
watermarked image. We also attack the watermarked image by using cropping and
adding noise and we got good results as well.

本文提出了一种新的数字水印算法，使用最不显著位（LSB）算法进行处理，将二进制值反转并根据图像的像素坐标嵌入水印，结果表明该算法相比于其他算法具有更强完好性、更高的 PSNR 与更高的鲁棒性。