17 results about "Image forensics" patented technology

The invention discloses a deep forgery detection method based on a visual language model, and relates to the field of image forensics. The deep forgery detection method based on the visual language model aims to combine multi-source information to improve the discrimination capability of the model on a real image and a generated image. The method comprises the following steps: firstly, extracting image features through an image encoder of a pre-trained CLIP model; meanwhile, a frequency domain enhanced counterfeit perception adapter is embedded in the image encoder to mine potential anomalies of counterfeit images in the image domain and the frequency domain. Secondly, a manual feature extraction module is provided, discriminative low-dimensional features are extracted from the four aspects of the edge, the texture, the frequency and the symmetry of the image, and the discriminative low-dimensional features are used as auxiliary information input in the forgery detection process, so that the robustness and the interpretability of the model are improved; meanwhile, the text cue words are converted into feature vectors through a text encoder of a pre-training CLIP model; and finally, the model predicts a forgery score by calculating the cosine similarity between the image features and the text features so as to realize the discrimination of the authenticity of the image. According to the method, the problem that the detection capability of the model on the cross-dataset is insufficient is effectively improved.

The invention discloses a deep counterfeit face image source tracing evidence obtaining method and system based on a diffusion model, and relates to the technical field of deep counterfeit face image evidence obtaining. The method comprises the following steps: constructing a robust watermark framework based on a diffusion model, wherein the framework comprises a diffusion model encoder, a watermark decoder and a freeze parameter auto-encoder; in a training stage, a face image and a watermark are constructed as conditions, a diffusion model encoder is guided to denoise, and a corresponding watermark image is predicted; the trained robust watermark framework based on the diffusion model is used for testing, a specific depth forging model is added in the sampling stage for guiding, and a more robust watermark image is generated through iterative denoising; in the evidence obtaining stage, the watermark in the forged image to be subjected to evidence obtaining is obtained through the watermark decoder. The method can effectively cope with different counterfeiting technologies, provides a more robust and reliable deep counterfeiting traceability evidence obtaining scheme, and has strong adaptability and wide application prospects.

The invention discloses a document image tampering detection method based on text aggregation and multi-frequency enhancement, and relates to the technical field of computer vision, image forensics and deep learning, and the method comprises the steps: obtaining a to-be-detected original RGB image, carrying out the multi-mode decomposition of the to-be-detected image, and obtaining a DCT coefficient graph, a corresponding quantization table, a high-frequency view and a low-frequency view; and inputting the original RGB image, the DCT coefficient graph, the corresponding quantization table, the high-frequency view and the low-frequency view into a document image tampering detection model for processing, and outputting a final detection result. The document image tampering detection model carries out feature dimension reduction and preliminary text aggregation through the vision-frequency fusion module, carries out coding and fusion through the multi-frequency feature extractor, generates comprehensive frequency features, carries out wavelet transform decoupling through the direction perception frequency decoupling enhancement module, and outputs tampered area masks based on the decoding prediction module. According to the invention, hidden tampering artifacts can be revealed more comprehensively.

This invention discloses a proactive forensic method for GIF face images based on spatiotemporal watermarking, belonging to the fields of image forensics and deep learning technology. This invention constructs a spatiotemporal adaptive residual encoder (STARE) and a deep integrity recovery decoder (DIRD), utilizing 3D convolution and adaptive attention mechanisms to capture the global spatiotemporal dependencies of the GIF, achieving coherent embedding of the watermark signal in the temporal dimension, eliminating visual flicker and enhancing resistance to temporal attacks. Simultaneously, this invention introduces an adversarial training mechanism, forcing the watermark information to be embedded in a deep spatiotemporal region robust to semantic reconstruction. Therefore, while ensuring high-fidelity visual quality, this significantly improves the watermark survival rate and forensic accuracy of GIFs when facing deepfake tampering.

This utility model provides a river dredging device for water conservancy supervision, belonging to the field of river dredging. It includes a tracked chassis, a dredging machine body mounted on the tracked chassis, a data acquisition unit, and an image evidence collection unit and a communication unit mounted on the dredging machine body. The data acquisition unit includes an acquisition chamber, a power supply located within the acquisition chamber, a cross-sectional data acquisition unit, a silt heavy metal information acquisition unit, a signal processing unit, and a signal storage and uploading unit, all electrically connected to the power supply. The acquisition chamber is located at the rear end of the tracked chassis. The signal acquisition ends of the cross-sectional data acquisition unit and the silt heavy metal information acquisition unit extend out of the acquisition chamber through sealed connectors. The signal receiving ends are respectively located within the acquisition chamber and are communicatively connected to the signal processing unit. The signal output end of the signal processing unit and the image evidence collection unit are communicatively connected to the signal storage and uploading unit. This solution facilitates the acquisition of complete river dredging data and is suitable for application in water conservancy supervision work.

The invention discloses an intelligent electricity utilization inspection system and method based on cooperative measurement of a master machine and a slave machine, and relates to the technical field of electric power detection. The system comprises a host, a slave, a low-voltage current clamp and a flexible current clamp, the host is integrated with a microprocessor, a touch screen, a voice broadcast, a high-definition camera, a Beidou positioning module, a Bluetooth printing module, a security encryption chip and a one-key alarm module; the slave machine measures primary side current through the high-voltage pincerlike mutual inductor and is in wireless communication with the host machine. The method comprises the following steps: system self-inspection and equipment connection; the master machine and the slave machine wirelessly and synchronously measure a primary side signal and a secondary side signal; the host executes an intelligent algorithm, automatically judges a wiring mode and generates graphical data, a correction coefficient and an electric charge compensation result; carrying out field image evidence obtaining and bar code identification; generating a standardized report containing the electronic signature and printing the standardized report on site; according to the invention, the functions of measurement, diagnosis, evidence collection, calculation, signature and printing are integrated into a whole, the whole process of electricity utilization inspection from detection to issuing is intelligent and electronized, and the working efficiency, evidence effectiveness and field safety are remarkably improved.

The invention discloses an image tampering positioning system and method based on compound eye bionics and uncertainty perception, and belongs to the technical field of image forensics and deep learning. The system provided by the invention comprises a multi-source parallel encoder which adopts images with three resolutions as input and retains tampering traces with different scales; the multi-resolution integration unit is used for dynamically fusing multi-resolution features through cross-scale attention; the chain type grouping interaction decoder is used for gradually eliminating redundant information and enhancing the discrimination capability of a tampered area; gaussian uncertainty loss is used for explicit penalty low-confidence prediction, and the positioning precision of the fuzzy boundary is improved. The method provided by the invention comprises the following steps: providing a bionic multi-resolution uncertainty sensing network, and realizing high-precision image tampering positioning by simulating a multi-aperture parallel sensing mechanism of an insect compound eye and combining multi-resolution input, chained grouping interactive decoding and Gaussian uncertainty loss.

This invention discloses a method for separating and identifying the authenticity of AI-generated content in distorted images, belonging to the fields of image forensics, AI-generated content detection, computer vision, and image credibility verification. This method addresses the problem that original metadata, content credentials, and generation parameters are easily lost or invalidated after images are transferred through platforms, screenshots, screen captures, or printed images. First, the method acquires the image to be detected and reads the image data, extracting propagation state features such as resolution ratio, compression marks, boundary regions, moiré patterns, paper texture, noise residuals, and file structure. Then, based on these propagation state features, the propagation state of the image to be detected is identified, and the corresponding detection branch is invoked to determine the effective content area, extracting content authenticity features and acquisition authenticity features respectively. Next, weights are assigned to various features according to the propagation state and dynamically fused to calculate the content authenticity risk result and acquisition authenticity judgment result. Finally, an authenticity separation result is generated, outputting a detection report containing the propagation state, acquisition authenticity, content authenticity, AI generation risk level, evidence items, and uncertainty explanation. This invention can distinguish between the authenticity of the image acquisition method and whether the content carried by the image has the risk of AI generation, even when the original image file information is invalid. It is applicable to the auxiliary identification of AI-generated content in scenarios such as screenshots, platform transfers, screen re-photographs, printed re-photographs, and mixed transmission distortion.

The invention discloses an image restoration evidence obtaining method and device based on a multi-color space, and relates to the field of image evidence obtaining in computer vision, and the method comprises the steps: converting an RGB color space image into a Lab color space version image and an HSV color space version image through color conversion; extracting features of the repaired and tampered images from the RGB color space image, the Lab color space version image and the HSV color space version image; the features in the three color spaces are adaptively fused through a channel attention mechanism based on space weighting, and features suitable for current image evidence obtaining are obtained; and based on the features suitable for the current image evidence obtaining, the repaired area is positioned, so that which area of the image is generated through an image repair algorithm is judged. Compared with the prior art, the method and the device have the advantage that excellent evidence obtaining performance can be achieved for the repaired tampered image with various complex repairing scenes.

The application discloses an image restoration forensics method based on multi-feature dynamic fusion, and belongs to the technical field of image forensics. Firstly, trace enhancement is performed on an input image by using spatial domain high-pass filtering and frequency domain high-pass filtering, and single input is expanded into multi-input features. Then, efficient feature learning is realized by combining RGB information and enhanced trace features through a multi-feature dynamic fusion encoder. Next, a multi-scale feature enhancement module is introduced to expand the multi-scale perception ability of the network. Finally, pixel-level detection and positioning are performed on the tampered area by using a decoder with a skip connection. The application fully utilizes the complementary advantages of various trace enhancement methods, combines dynamic convolution and multi-scale context information, improves the robustness and generalization performance of the forensics model, and can realize high-precision identification and positioning of the image restoration area in different forensics scenes.

The invention discloses an intelligent regulation and control method for an intelligent logistics unmanned metering system. Vehicle appearance images and three-dimensional point clouds are collected, and a parking geometric constraint set and a cargo compartment loading element map are generated; building a parking mechanical consistency criterion based on the constraint set and the fluctuation characteristics of the weighing sensor, and judging an effective weighing state and latching data when a convergence condition is met; in combination with historical cargo density distribution and the geometric volume of the voxel map, visual auxiliary quality estimation is generated, and the visual auxiliary quality estimation and a sensor output residual error are checked to obtain a measurement consistency confidence coefficient; when the confidence coefficient is low, an abnormity diagnosis sub-process is activated, wheel suspension and axle load distribution rationality are analyzed by comparing gravity center projection with wagon balance pressure center offset, and a cheating risk score and an invalid weighing mark are generated; and dynamically selecting an output mode according to confidence and risk scores, directly outputting a quality result when the confidence is high and the risk is low, triggering high-definition image evidence obtaining and starting an arbitration process when the risk is medium, and refusing metering and recording a log when the confidence is low or the risk is high.

The invention discloses a depth attributable watermarking method oriented to a multi-person scene, and belongs to the technical field of image evidence obtaining and deep learning. According to the method, a multi-face encoder-decoder architecture is constructed, an end-to-end full convolutional network is adopted, an original image is used as a whole to be input, parallel recognition is performed, watermarks are embedded into all target face regions, one-time efficient parallel processing and cross-region feature extraction of multiple face targets are realized, and preprocessing steps are simplified fundamentally; in addition, a selective region is constructed to supervise loss, a forged face positioning mask is introduced as a loss weight, the watermark extraction loss of a compulsory decoder is only calculated in a tampered region, the watermark extraction capability is coupled with the positioning of a forged region, and pixel-level interpretable positioning judgment is realized. The invention also provides a dual attribution mechanism, and provides accurate positioning and attributable source fingerprints provided by watermarks. Through successful recovery of attributable watermarks, a complete evidence closed loop of extracting traceability watermarks from positioning watermarks is realized.

The present invention provides a GAN image forensics method that fuses robust features of color spaces. By combining the advantages of handcrafted features with DNN, a reliable and efficient detector is designed. Under the guidance of the experience of selecting color channels, the features are input into the DNN for training, and good detection performance can be achieved, including the following steps: Step 1, convert the RGB image into the HSV color space and the YCbCr color space; Step 2, calculate the mean of the pixels in each color channel in Step 1, calculate its correlation coefficient, and calculate the chi-square distance for the correlation coefficients of each color channel; Step 3, select the four color channels with the largest chi-square distance; Step 4, extract the cross-color space co-occurrence matrix using the color channels selected in Step 3; Step 5, input the features in Step 4 into a shallow neural network for training to obtain a model and use it for final classification.

This invention discloses a dynamic forensic method and system for AI-generated images based on hyperbolic space. The method includes: extracting multi-scale features of the image to be forensic and embedding them into hyperbolic space to obtain hyperbolic embedding anchor points; generating a first forensic judgment result by calculating the distortion degree and penalty value between the anchor point and the real image prototype. Secondly, when the preliminary result is in an ambiguous range, the system dynamically triggers a cross-modal forensic verification link, performing a deep comparison combining physical geometry and semantic logic common sense to arrive at a final judgment conclusion. Finally, if the image is confirmed to be AI-generated, the system will accurately locate candidate generation engines through tangent space retrieval and utilize a proxy network to trace the contribution ranking of training data, ultimately outputting a tamper-proof structured forensic report chain. This invention effectively amplifies the hidden artifacts of high-fidelity AI images by utilizing the characteristics of hyperbolic space, achieving high-precision identification and dynamic balance of system computing power while providing complete engine tracing and data attribution capabilities.

The present invention discloses a method and system for detecting false facial images based on image forensics technology. The method mainly includes five steps: Step 1, in the video preprocessing module, Dlib is used to intercept the faces in the original video as a preprocessed data set; Step 2, in the interpolation and underlying feature module, the image is preprocessed by the SRM filter, and then the dimension is reduced by the residual network and the feature extraction is performed by XceptionNet; Step 3, in the background noise module, the PRNU algorithm and the attention mechanism are used to obtain an output vector with background noise information; Step 4, in the video modification detection module, the outputs of the above modules are spliced and passed through the fully connected layer to obtain the modified detection results. Step 5, in the visualization display module, Web interaction technology is used to realize the visualization display of the results. The present invention can effectively improve the accuracy of false face detection, which is of great significance for maintaining a healthy and green network environment.

The invention relates to a public health information authenticity prediction method based on image recognition, and the method comprises the following steps: obtaining a to-be-detected picture uploaded by a user, and recording public health information in the to-be-detected picture; firstly, a metadata checking tool is called to judge whether a picture PS event exists in a to-be-detected picture or not, and if yes, a prediction result with suspected authenticity is directly output; if not, next judgment is carried out; then, calling an image evidence obtaining tool to judge whether a picture editing event exists in the to-be-detected picture or not, and if yes, directly outputting a prediction result with suspected authenticity; if not, next judgment is carried out; and executing an edge detection algorithm on the to-be-detected picture to obtain an edge image, performing edge blurring condition analysis on the edge image, if so, outputting a prediction result with suspected authenticity, and if not, outputting a prediction result with true image and ending detection. The method can perform authenticity analysis on the to-be-detected picture uploaded by the user and automatically output the authenticity prediction result, is convenient for the user to use, and is high in generalization performance.

The invention discloses an image tampering positioning method and system based on label decoupling, and belongs to the technical field of image evidence obtaining and deep learning. According to the method, a tampering mask is divided into a body area (an easy-to-predict interior) and a detail area (a difficult-to-predict boundary) through a label decoupling strategy, a double-span hourglass Transform encoder (DH-ViT) and a bidirectional decoupling pyramid decoder (BDPD) are designed to realize separation, extraction and optimization of two types of features, and intelligent fusion of the features is realized through a body-detail adaptive relation module (BARM). The limitation of the prior art is comprehensively broken through from three levels of label design, network architecture and feature fusion, and the problems that the positioning precision and the boundary fine positioning capability are difficult to guarantee at the same time and the uncertainty estimation of a tampered area is insufficient in the prior art when facing an image in a complex scene are effectively solved. And the problems of boundary blur, false detection or missing detection of a detection result are solved.