jpeg encoder  (Pegasus Imaging Corporation)

Journal: Scientific Reports

Article Title: MSCSCC-Net: multi-scale contextual spatial-channel correlation network for forgery detection and localization of JPEG-compressed image

doi: 10.1038/s41598-025-97555-6

Figure Lengend Snippet: Overall Architecture of the proposed MSCSCC-Net. Deep feature extraction module extracted different scales features from input JPEG-compressed image and then used for forgery detection and localization. The detection head determines if the image is forged based on the prediction score. As we move from Mask 4 to Mask 1, the precision of forgery localization increases. For instance, Mask 1 corrects Mask 4’s prediction that confuses the forged area with the copied one.

Article Snippet: To add JPEG-compressed artifacts, we use the above test datasets to generate JPEG-compressed images by the MATLAB JPEG encoder, and each image’s quality factor ranges uniformly from 10 to 100 in increments of 10. (2) Metrics: In accordance with earlier research , we compute the PSNR, SSIM, and PSNR-B for a quantitative evaluation of the restored image to compare JPEG artifact removal performance.

Techniques: Extraction

Journal: Nature Communications

Article Title: Integrated photonic encoder for low power and high-speed image processing

doi: 10.1038/s41467-024-48099-2

Figure Lengend Snippet: Comparison of energy consumption (given by Energy/MAC) as a function of number of inputs pixels N for encoding via matrix multiplication using electronic approaches such as GPU, SoC, or ASIC-based (black solid line with a red band) and the presented optical approach using a photonic encoder with average transmission \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${T}_{{scatter}}=20\%$$\end{document} T s c a t t e r = 20 % (blue solid line). For the electronic approaches, typical energy efficiency of these digital accelerators is on the order of ~1 pJ/MAC and the red band shows the range of values for different accelerators. For the photonic approach, different color-coded lines correspond to the different components contributing to the total energy consumption such as the laser (dashed red line), modulators (dashed yellow lines), and detectors (dashed magenta line). The vertical gray line corresponds to energy consumption values for an 8 × 8 kernel or a 64-input pixel block. The energy consumption is dominated by the input laser and the overall energy efficiency of the presented optical approach improves as N or number of input pixels increases.

Article Snippet: These SoCs typically include ARM cores for general-purpose computing, memory interface, and device control, along with specifically designed hardware codecs (e.g., JPEG/HEIF encoder in Canon DIGIC) or image-processing ASIC (e.g., Apple A16 Bionic) for JPEG compression and decoding.

Techniques: Comparison, Transmission Assay, Blocking Assay