Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

5 results about "Jpeg compression" patented technology

Lightweight watermarking method for latent space diffusion model robust image attribution

This invention discloses a lightweight watermarking method for robust image attribution based on latent space diffusion models. The method uses low-dimensional feature vectors as the watermark carrier: first, a feature watermark library is constructed; then, a feature-noise encoder and a noise-feature decoder are trained. The encoder maps the feature watermark to initial latent space noise that satisfies a standard Gaussian distribution and inputs it into the latent space diffusion model to generate an image. When attribution verification is required, the image to be verified is inverted to recover the initial latent space noise, and the corresponding feature watermark is reconstructed by the decoder. The identity is determined using the cosine similarity between the reconstructed watermark and the original watermark in the feature watermark library. This invention maintains the quality of the generated image while exhibiting strong robustness to common distortions such as JPEG compression, cropping, random discarding, blurring, and brightness variations, and significantly reduces the overhead of watermark storage and matching computation.
Owner:HANGZHOU UNIV OF ELECTRONIC SCI & TECH PINGHU DIGITAL TECH INNOVATION RES INST CO LTD

A SOC-based dual-channel image acquisition processing method and local on-orbit programming method

This application discloses a dual-channel image acquisition and processing method and a local on-orbit programming method based on a System-on-Chip (SOC). A first SOC processing unit acquires visible light images, and a second SOC processing unit acquires short-wave infrared images; both undergo preprocessing, target extraction, and JPEG compression. Both processing units utilize heterogeneous SOC chips with integrated RISC-V CPUs and FPGAs, and are independently equipped with DDR3 and SPI NOR Flash. The FPGA integrates connected component labeling and centroid extraction modules, employing a single-scan algorithm for parallel processing and directly outputting centroid coordinates at the end of a single frame scan. Local on-orbit programming uses function-level BIN splitting and CRC comparison, only programming the change modules. JPEG compression adjusts image parameters through configuration registers and automatically reloads the quantization table. This application achieves parallel acquisition of visible and infrared light, real-time centroid extraction, incremental programming, and flexible compression, suitable for aerospace attitude control and remote sensing imaging.
Owner:ZHUHAI CORE DISCOVERY MICROELECTRONICS CO LTD +1

A two-stage watermark embedding method and system for JPEG enhancement

The application discloses a kind of JPEG enhanced two-stage watermark embedding method and system, method includes: constructing the watermark model including encoder, decoder, discriminator and noise layer;Optimal watermark model is obtained using two-stage training strategy, in the joint training of encoder and decoder in the first stage, introduce JPEG noise layer, in the second stage, fix the encoder and fine-tune the decoder using multiple noise attacks;Wherein, the encoder extracts features through the multi-path global-local aggregation module, and uses the channel-space collaborative attention mechanism in the redundancy enhancement module, and fuses the frequency domain statistical information to optimize the embedding position;After the carrier image to be embedded with watermark is preprocessed, it is input into the watermark model loaded with optimal model weight together with watermark information, and the corresponding watermark image is output. The application effectively improves the robustness of the watermark to JPEG compression and other attacks, while ensuring the high visual quality of the watermark image.
Owner:FUJIAN UNIV OF TECH

A method for locating tampering of a document image based on halftone noise and artifact enhancement

The present application relates to a kind of based on halftone noise and artifact enhancement document image tampering positioning method.The method constructs halftone noise perception stream, utilizes denoising residual mechanism to extract the micro halftone statistical law damaged by tampering;Frequency domain perception stream is constructed, decouples luminance and chroma in YCrCb color space, removes low-frequency background by combining adaptive frequency domain enhancement and adaptive high-pass filter, and accurately captures high-frequency quantization artifact;Covariance-based feature fusion mechanism is constructed, spatial domain, frequency domain and halftone noise domain features are cascaded and fused, and the conflict of multi-modal heterogeneity is relieved to accurately locate tampering area.The method is for the authenticity verification scene of document image disturbed by complex post-processing such as JPEG compression, scaling, and good results are obtained in positioning accuracy and robustness.
Owner:CHANGSHA UNIVERSITY OF SCIENCE AND TECHNOLOGY

JPEG compression verification method, device and storage medium

The application discloses a JPEG compression verification method and device and a storage medium, relates to the field of data processing, and comprises the following steps: acquiring an original image frame and a compressed image; performing grayscale processing and image cutting operation on the compressed image to acquire a plurality of compressed image blocks and grayscale image blocks; performing edge detection on the grayscale image blocks to acquire a binary edge image; acquiring an affine transformation matrix according to the pixel values of all pixels in the binary edge image; generating a plurality of feature image blocks according to the original image frame, image configuration parameters, each compressed image block and the affine transformation matrix; performing feature comparison on the i-th compressed image block and the i-th feature image block to acquire an i-th similarity comparison result; comparing the i-th similarity comparison result with a preconfigured preset threshold value respectively to acquire an i-th comparison result; and acquiring a compression verification result when the i acquired comparison results meet a preset stop condition. The method has high compatibility, low cost and high efficiency.
Owner:SHANDONG YUNHAI GUOCHUANG CLOUD COMPUTING EQUIP IND INNOVATION CENT CO LTD