54 results about "Image forgery" patented technology

The invention discloses an incremental counterfeit face image identification method based on cross-domain feature alignment, which belongs to the field of deep counterfeit detection, and comprises the following steps of: constructing a face image counterfeit detection model, extracting a network by taking Xception as a main feature when the model is constructed, a task adaptive weight correction module, a class awareness supervision comparison learning module, a double knowledge distillation module and a classification discrimination module are synchronously introduced; defining a task sequence, and constructing a task sample set and a task test set for subsequent model training and testing; a domain chain progressive training mechanism is adopted to train the face image forgery detection model, and the training process is composed of a basic stage and a plurality of incremental task stages; after training of each task is finished, testing is carried out; and obtaining a current to-be-identified face image, and inputting the final face image counterfeiting detection model to obtain an identification result. According to the method, the accuracy and generalization of face image counterfeiting detection can be effectively improved.

The invention relates to the technical field of image detection, and provides an image forgery detection method based on a multi-modal large language model, which comprises the following steps: inputting a to-be-detected image into the multi-modal large language model; the multi-modal large language model outputs an authenticity identification result of the to-be-detected image; wherein the multi-modal large language model has three parallel expert branches of physical consistency, semantic consistency and underlying structure clue analysis. According to the method, semantic information in the image is perceived and the context logic and the physical logic of the image are understood by fully utilizing the powerful priori knowledge, the deep semantic understanding capability and the chained reasoning capability of the multi-modal large language model, and meanwhile, complex reasoning and explanation can be performed on a forged image through a natural language.

The invention discloses a method for detecting image forgery and computing equipment. The method for detecting image counterfeiting comprises the following steps: extracting text information in a to-be-detected image to obtain a first text; generating image description information of the to-be-detected image to obtain a second text; and based on the first text and the second text, determining whether a logic anomaly exists in the to-be-detected image.

Provided are an apparatus and method for verifying forgery of a medical image using a hash value based on meta information of the medical image.SOLUTION: The forgery verification apparatus 400 includes a memory configured to store patient-specific DICOM files and a processor functionally connected to the memory, and the processor is configured to, when issuance of a DICOM file is requested, search for the requested DICOM file among the patient-specific DICOM files, generate an issuance number associated with the issuance, extract a part of meta information of the DICOM file, generate a first hash value using the part of the meta information and the issuance number, and store the first hash value in the memory in association with the issuance number. While providing a copy of a DICOM file to an external storage device, a first hash value is inserted into a designated tag area of the copy as forgery verification information.SELECTED DRAWING: Figure 1

The invention provides an image forgery detection method and system based on asymmetric anchoring of a multi-modal large model, and belongs to the technical field of image detection processing. Truth value anchor point features and to-be-optimized intermediate features of an input image are extracted; an asymmetric strategy is executed based on the authenticity category of the image, and anchoring alignment loss is introduced only for the real image to anchor real feature distribution; extracting global semantic features, and mapping the global semantic features into the authenticity category probability of the image through a classification projection head; and generating a space alignment error graph by using the deviation between the intermediate feature to be optimized and the true value anchor point feature, injecting the space alignment error graph into a positioning decoder, and generating a forged region mask by combining the output feature of the positioning encoder. According to the method, a true value anchor point is redefined, and an asymmetric anchoring mechanism is utilized to force real image features to return to real world priori, so that the problem of characterization drift is solved; and generating a spatial error graph by using the feature alignment deviation, thereby realizing stable learning of forged clues and realizing positioning of an accurate tampering region.

The application relates to an image forgery positioning device and method based on multi-scale attention, and belongs to the technical field of image processing, solving the problems that the edge of a positioning area is not clear enough and the positioning result is not accurate enough in the prior art. The application generates synthetic forged images of various types and modes through a traditional forged image synthesis module, enhancing the generalization of the device to various types of forgery. The forged area edge feature extraction module extracts and strengthens the part related to the forged area edge in the forged area feature, fully utilizes the forged traces brought by the edge operation, and has high edge definition. The multi-scale spatial attention module gradually fuses spatial features of different scales, provides coarse-grained forged area prediction from small-scale features, combines large-scale features and edge features for fine-grained forged area prediction, and realizes more precise forged area positioning. The device training is easy to control and sufficient.

The invention discloses a layered fine-grained image forgery detection method and a layered fine-grained image forgery detection system. And the authenticity of the input image is preliminarily judged through the authenticity judgment module. Constructing a multi-branch pixel-level counterfeit positioning network, and obtaining multi-scale feature representation from low resolution to high resolution through a feature extraction backbone network; a high-resolution forged mask is obtained through pixel-level positioning network prediction; and the decision network constructs a coarse-to-fine reasoning path according to the multi-level label system, sequentially completes forgery property judgment, forgery type judgment, method-level traceability and platform-level traceability, and outputs a conditional probability of a corresponding-level label as a traceability result. The method has a unified multi-level label system, the systematicness and the accuracy of detection are remarkably improved, the source and the position of counterfeiting are visually presented through mask positioning and hierarchical classification, and the interpretability is high.

The invention discloses an image forgery detection method based on a camera signal shaping effect, and belongs to the technical field of image forgery generation security, and the method comprises the steps: S1, obtaining original single-channel Bayer format data, dividing the original single-channel Bayer format data into space block units, generating an interpolation index template, matching a specific algorithm index for each image block according to a preset algorithm library and an interpolation index template; and S2, executing verification and detection of an interpolation index template generation mode at a detection end, and authenticating the authenticity of the image and accurately positioning a tampered area by comparing the consistency of physical signal characteristics of the image and encryption verification logic. According to the invention, the problem that high-precision positioning and identification of image tampering behaviors cannot be realized in the prior art is solved. On the premise of not changing the physical hardware of the camera, the verification information is embedded into the texture structure of the image by utilizing the variability of the demosaicing algorithm, so that the problems of image authenticity traceability and local tampering positioning are solved from the source.

The one or more embodiments of the specification disclose a method, device and equipment for image forgery detection. The method comprises: performing feature extraction on each pixel point in a to-be-detected image to obtain image features corresponding to each pixel point in the to-be-detected image; inputting the image features corresponding to each pixel point in the to-be-detected image into a forgery detection model to perform forgery feature similarity matching between the image features corresponding to any two pixel points in the to-be-detected image, and obtain a forgery feature similarity value between any two pixel points in the to-be-detected image; determining, according to the forgery feature similarity value, a forgery probability map of the to-be-detected image corresponding to each pixel point in the to-be-detected image; and in a case where a proportion of pixel points with a forgery probability value exceeding a preset probability in the forgery probability map exceeds a first preset proportion, determining a forgery region in the to-be-detected image according to the proportion of pixel points with the forgery probability value exceeding the preset probability in the forgery probability map.

The application provides a picture forgery detection method, comprising: extracting frequency domain features and spatial domain features of a to-be-detected picture and a plurality of derived pictures, wherein each derived picture is generated after a first operation is performed on the to-be-detected picture, and the to-be-detected picture is a picture of a preset size; determining intermediate feature vectors of the to-be-detected picture and the derived pictures according to the frequency domain features and the spatial domain features, respectively; inputting the intermediate features into a true-false discriminator and a model tracer in parallel, wherein the true-false discriminator is a binary classifier, and the model tracer is a multi-class classifier; determining a fake or real detection result according to the intermediate feature vectors by using the true-false discriminator, and generating a multi-class probability distribution according to the intermediate feature vectors by using the model tracer, wherein the multi-class probability distribution refers to a probability distribution of a picture forged by a forgery model; outputting information indicating whether the to-be-detected picture is real or fake based on the detection result of the true-false discriminator and the probability distribution generated by the model tracer, and outputting the probability distribution at least in the case that the picture is fake. Corresponding systems, program products, and the like are also provided.

The invention discloses an image forgery positioning system based on a bimodal vision Mangbar network, which relates to the technical field of image forgery positioning and comprises a model construction unit and a forgery positioning unit. The model construction unit is used for preprocessing the to-be-detected image and acquiring an RGB modal image and a corresponding brightness gradient modal image; respectively carrying out feature extraction to obtain RGB features and corresponding brightness gradient features, carrying out fusion to obtain fusion features, and carrying out decoding through a decoder to obtain prediction maps of all stages; and the forgery positioning unit is used for receiving the prediction map of each stage, obtaining a final prediction map by adopting a voting mechanism, setting a confidence coefficient threshold value, judging an area of which the pixel value is greater than the confidence coefficient threshold value as a forgery area, superposing the final prediction map subjected to morphological operation processing with an original input image, and outputting a visual positioning result. According to the method, RGB and brightness gradient bimodal features are combined, and the positioning precision of weak-trace and high-fusion-degree forged areas is greatly improved.

The invention discloses a forgery positioning method based on attention enhancement and adaptive frequency selection, and belongs to the technical field of image forgery detection. The invention aims to solve the problem of poor positioning precision and robustness caused by inaccurate feature capture of a forged area and insufficient utilization of multi-scale and frequency information in the existing forged positioning technology. The scheme comprises the following steps: extracting multi-scale spatial features of an input image through an encoder; channel and space attention weighting is carried out on the multi-scale features by using an attention enhancement module so as to enhance and counterfeit related features; carrying out discrete cosine transform and adaptive weight learning on the enhanced features by adopting an adaptive frequency selection module, screening effective frequency components and carrying out cross-domain fusion; and finally, generating a positioning mask of the forged region based on the fusion features. The method can effectively improve the positioning accuracy of the forged area in the image and the robustness in a complex scene, and is suitable for digital media evidence obtaining and content security auditing.

The application discloses a kind of deep fake video detection methods based on weighted feature pyramid, belong to video identification technical field;Contain the following steps: construct fusion fake attention map's weighted bidirectional feature pyramid network, introduce the multi-task learning mechanism based on explicit attention mechanism;Training deep fake video detection network;Cut high-quality deep fake video in face information;The high-quality picture after processing is input to the deep fake video detection network after training and output whether belong to fake video.The application makes full use of the advantage that convolutional neural network shows in the image fake detail extraction in degree video fake detection, the fusion process of low layer and high layer feature map is supervised by fake attention map, while reducing information redundancy, the sensitivity of model to high-quality fake area is enhanced.Feature map is supervised by the generated fake position label, explicitly guide model to focus on sensitive area prone to artifact, improve the generalization ability of model.

The invention relates to an image forgery detection method and device based on multi-view representation preprocessing, and is applied to the technical field of computer vision, and the method comprises the steps: processing a to-be-detected image through N preprocessing modes, and obtaining N groups of to-be-detected features; inputting the N groups of to-be-detected features into a multi-view counterfeit detection model, and performing feature extraction on the N groups of to-be-detected features to obtain N groups of to-be-detected feature vectors; routing the N groups of to-be-detected feature vectors to N perspective expert networks by using a gating network in the hybrid expert module, and outputting N groups of to-be-detected optimized feature vectors; respectively routing N groups of to-be-detected feature vectors output by the target feature extraction layer and N groups of to-be-detected optimized feature vectors output by the first M-1 hybrid expert modules to L high-dimensional feature expert networks by using a gating network in the last hybrid expert module, and outputting a fused to-be-detected feature vector; and by extracting and processing the classification mark, outputting a counterfeit category. And the detection precision can be improved.

The present document discloses an image processing method, device, electronic equipment, storage medium and program product. The method comprises: performing multi-layer feature extraction on a first image to obtain a shallow feature map and a middle feature map of the first image; performing enhancement processing on an artifact area of the shallow feature map to obtain a first embedding representation of the first image; transforming the middle feature map to a frequency domain to obtain a second embedding representation of the first image; and classifying the first image based on the first embedding representation and the second embedding representation to obtain a first classification result, the first classification result representing the authenticity of the first image. Thus, without relying on the high-level semantics of the image, the authenticity of the image is determined by using the microscopic traces introduced by the image forgery process and not easily perceived by the human eye, and even when facing high-fidelity forged images, the accurate detection capability can still be maintained.

The application discloses a multi-face image local fake feature intelligent detection method based on a generative adversarial network. The method comprises the following steps: S1: inputting a face image true and false data set into a generative adversarial network for face key point extraction training; S2: determining position information positioning of the face key points to obtain a position set of face key local points; S3: performing feature segmentation on the multi-face image to obtain corresponding features of the face key local points; S4: inputting the face key local point position set and the corresponding features into the generative adversarial network to generate realistic false data to achieve the purpose of deceiving a discriminator; and S5: using a radial basis function as a kernel function to help capture the relationship between fake features and real features, and using a support vector machine classification model to perform fake detection. The method can realize face fake feature point positioning while consuming less computing amount, accurately detect local fake features of a face image, and is suitable for multi-angle face image fake detection.

This invention relates to the field of image detection technology, and more particularly to a method, device, and storage medium for cross-domain AIGC image forgery detection based on unsupervised domain adaptation. The method includes: S1: preprocessing the source and target domain image sets to obtain dual-stream images; S2: extracting high-dimensional image features from the dual-stream images in the backbone network and then reducing the dimensionality; S3: dividing the reduced-dimensional feature vectors into a supervised classification branch and an unsupervised alignment branch, calculating the distribution distance in the unsupervised alignment branch to obtain the transfer loss; S4: calculating the cross-entropy classification loss in the supervised classification branch to construct a joint loss function, updating the weights of the backbone network and the classifier to obtain a detection model, and performing authenticity identification on images in the unknown target domain. This invention significantly improves the generalization ability and robustness of the AIGC forged image detection model in cross-generator scenarios by removing the global average pooling layer to retain microscopic forgery traces and combining multi-kernel maximum mean difference to achieve explicit alignment of feature distributions between the source and target domains.

The application discloses a student model training method, an image forgery detection method and computer equipment, and belongs to the image detection field. The image forgery detection method comprises the following steps: determining a target image to be detected; calling a trained student model based on the target image to generate a detection result; wherein the student model is trained by fusing a synthetic forgery feature, training images and intermediate features; the training images are provided by more than two domains; the intermediate features are generated by calling a corresponding teacher model based on the training images; the synthetic forgery feature is generated by calling a teaching assistant model based on all the intermediate features; and the synthetic forgery feature refers to a feature corresponding to common information in all the intermediate features. The method can improve the accuracy of identifying whether an image is a forged image.

The invention discloses an AI generated image forgery detection method based on multi-expert collaboration, which belongs to the field of image forgery detection, and comprises the following steps: dynamically calculating a feature fusion weight ratio through a feature correlation evaluation mechanism, generating a comprehensive multi-domain fusion feature vector, and dynamically adjusting a weight update rate according to image content complexity, so as to obtain a multi-domain fusion feature vector; and finally, efficient authenticity discrimination is realized through a discrimination model. According to the method, the high-dimensional feature vector is processed through dimension reduction analysis, the calculation efficiency is ensured, meanwhile, the potential risk area is marked, and an accurate detection result is output.

The present application relates to the field of fake image detection, and provides a fake image detection method, device, medium and product, the method comprising: dividing an input image into multiple local regions, and constructing a region dependency graph of the local regions; extracting local style features from the region dependency graph using a local network model; extracting global style features of the input image using a global network model; performing attention fusion on the local style features and the global style features using an attention model to obtain a fusion vector; and performing image forgery detection on the fusion vector using a classifier; wherein the local network model, the global network model, the attention model and the classifier are optimized through training. The present application can maintain high recognition accuracy and robustness in sample-scarce, local detail forgery and cross-domain forgery detection scenarios.

The invention relates to the technical field of image forgery detection, and discloses a diffusion model image restoration forgery-oriented multi-view fusion and regional decoupling detection system, which comprises a forgery trace extraction module and a tampered region positioning fusion module, the forgery trace extraction module comprises a noise residual extractor, a high-frequency texture extractor, a cross-view fusion device and a multi-stage contrast learning device. According to the system, through a multi-view feature fusion mechanism and a region decoupling strategy, the detection problem caused by visual consistency, edge smoothness and noise distribution homogeneity of a diffusion model repair image is effectively solved; the innovative multi-level contrast learning framework can forcibly separate the feature representation of the counterfeit and real areas, and significantly improve the ability to capture weak counterfeit traces; the dynamic interactive fusion module realizes collaborative optimization of main body and edge features through a multi-scale channel attention mechanism; the DMIL-Net can rapidly and accurately mark the diffusion repair area in the image, and the manual checking burden is relieved.

The invention discloses an image detection method and a related product. The method comprises the following steps: collecting a real face image and a real non-face image; generating a plurality of middle face images based on the real face image, and generating a plurality of middle non-face images based on the real non-face image; according to the mask image corresponding to the real face image, performing hybrid processing on the plurality of middle face images to generate a forged face image, and according to the mask image corresponding to the real non-face image, performing hybrid processing on the plurality of middle non-face images to generate a forged non-face image; determining a target non-face image based on the difference degree between the real non-face image and the forged non-face image; performing model training based on the real face image, the counterfeit face image and the target non-face image to obtain a deep counterfeit detection model; and detecting the to-be-detected face image based on the deep forgery detection model to obtain a detection result. Therefore, the generalization ability of the deep counterfeiting detection model can be improved, and the detection effect is improved.

The invention relates to the technical field of computer vision, and discloses an image forgery detection model interpretability analysis method and system, and the method comprises the steps: extracting the middle layer features of an image forgery detection model to be interpreted, and generating a semantic feature map based on the non-negative matrix decomposition of sparsity constraint; performing feature importance pre-screening on the semantic feature map to obtain an important feature map; for each important feature map, positioning a high activation area and extracting an image block, and analyzing a dominant frequency component and a bandwidth of the image block corresponding to the high activation area; constructing a band elimination filter in the frequency domain of the original image, generating a disturbance image, and endowing each feature with an initial weight based on a decision distance; and performing grouping fusion on the features according to the symbols of the initial weights, and respectively generating final visual saliency evidence graphs which support counterfeiting and reality. According to the invention, through combination of the non-negative matrix factorization and the frequency domain disturbance shielding method, the interpretability of the image forgery detection model can be effectively improved.

The application relates to the technical field of image processing, and discloses an image forgery hierarchical attribution method based on hyperbolic space and VMamba, which comprises the following steps: obtaining fingerprint stream global features according to an original input image; respectively mapping the fingerprint stream global features into general forgery features and specific fingerprint features through different residual network modules, and obtaining an orthogonal constraint loss and a semantic decoupling loss according to the general forgery features and the specific fingerprint features; obtaining a learning prototype set of each class of each layer in a first layer to a third layer according to a hyperbolic distance, updating feature extraction network parameters according to the learning prototype set, minimizing a total loss function, and finally obtaining a feature extraction model; inputting a new original input image into the feature extraction model to obtain a prediction probability of a sample being a real image and a prediction probability of the sample being a forged image, and outputting an attribution path according to the prediction probability and the prediction probability. The application significantly improves the classification accuracy of a fine-grained model attribution.

The application discloses a deep fake video detection method fusing ViT and spatial features, belongs to the technical field of video recognition, and is used for detecting deep fake videos. The application comprises the following steps: constructing a neural network fusing ViT and spatial features; training a deep fake video detection network; acquiring face data information in a deep fake video; inputting processed video information into the trained deep fake video detection network and outputting whether the video belongs to a fake video. The application fully utilizes the advantages of a convolutional neural network in extracting image fake details in deep video fake detection, combines orthogonal convolution, attention mechanism, residual connection and other ideas, maintains the complexity of the model, improves the accuracy of deep fake video detection, and has relatively stable detection performance in videos generated by various fake technologies.

The present application relates to the technical field of image detection, and more particularly to a lightweight AI-generated image detection method based on multi-feature fusion and progressive block optimization, comprising: S1: preprocessing the input image to generate an RGB original image, an SRM artifact feature map and an LBP-HOG texture feature map; S2: constructing a parallel multi-branch feature extraction network to extract high-level semantic features, residual artifact features and local texture features respectively; S3: adopting a progressive block collaborative training strategy, independently training each branch feature extractor to convergence in the first stage, and loading the optimal weight of each branch to train an adaptive fusion layer in the second stage; and S4: obtaining an image forgery probability by weighting and combining the outputs of each branch through the fusion layer, so as to realize true and false image classification. Through the multi-dimensional feature complementation of semantics-artifact-texture and the training mechanism of phased optimization, the present application significantly improves the detection accuracy and model convergence stability of AI-generated images, and is suitable for general image authenticity identification scenarios.

Techniques for predicting whether a submission includes a forged image. A computer system receives a submission from a user that includes an image and image metadata, such as an identifier for the user and a User-Agent string value. An image pixel embedding is generated from the image, and a profile embedding is generated from the image metadata. The image embedding is indicative of whether the image is similar to known image forgeries. The profile embedding is generated from a user activity embedding indicative of User-Agent values associated with the user identifier. The profile embedding is generated using a machine learning model that uses stored parameters to associate user activity, device information, and forgery groups. The profile embedding thus indicates whether the user is associated with known image forgeries. The image pixel embedding and profile embedding are then used by a neural network to output a forgery prediction.

An electronic device is provided. The electronic device includes a sensor, memory configured to store plurality of fingerprint templates, each of the plurality of fingerprint templates is an embedding vector indicating each of plurality of registered fingerprint images, and at least one computer program, and at least one processor communicatively coupled to the sensor and the memory, wherein the plurality of registered fingerprint images comprises a forged fingerprint image made by forging a fingerprint of a user, an abnormal state fingerprint image comprising an obstacle obstructing fingerprint authentication, and a normal state fingerprint image which is either a successfully registered fingerprint image or a fingerprint image matching the successfully registered fingerprint image, and wherein the at least one computer program includes instructions that, when executed by the at least one processor individually or collectively, cause the electronic device to acquire, using the sensor, an input fingerprint image indicating a fingerprint image input by the user, identify whether the input fingerprint image matches at least a part of the plurality of registered fingerprint images based on the plurality of fingerprint templates, in case that the input fingerprint image matches the at least a part of the plurality of registered fingerprint images, generate at least one virtual fingerprint image, based on the input fingerprint image matching the at least a part of the plurality of registered fingerprint images, store a template of the input fingerprint image and at least one template of the at least one virtual fingerprint image in the plurality of fingerprint templates, and train a fingerprint generation artificial intelligence model to generate a fingerprint image similar to the at least one virtual fingerprint image or the input fingerprint image.

This invention discloses an image forgery detection and localization method based on the lottery hypothesis and masked autoencoder. The steps include: 1. Pre-training the image using a masked autoencoder to extract prior knowledge of the natural image; 2. Identifying parameters sensitive to forgery detection tasks during the pre-training stage based on the lottery hypothesis to obtain a gradient mask; 3. Constructing a multi-source forgery perception network, implementing sparse fine-tuning optimization based on the gradient mask, and training the network to output accurate detection and localization results. This invention combines the feature extraction capability of the masked autoencoder with the parameter selection strategy of the lottery hypothesis, significantly improving the accuracy and generalization of forgery detection and localization through sparse fine-tuning and multi-source feature fusion.

This invention discloses a method for analyzing model performance and determining authenticity in scientific and technological literature, relating to the field of intelligent paper analysis. The method includes: acquiring multimodal information from the paper; extracting parameter data of the target model and inputting it into a training budget calculation model and an inference budget calculation model to obtain the training budget and inference budget; extracting parameter data of a baseline model for comparison and obtaining its training budget and inference budget; obtaining parameters from the paper regarding the performance improvement of the target model relative to the baseline model; inputting the training budget and inference budget of the target model and the baseline model, along with the performance improvement parameters, into a comparison model; and outputting the category of the actual performance improvement reasons for the target model in the paper based on the comparison model. This invention can effectively distinguish whether the model performance improvement stems from algorithm improvement or computational power stacking; it can also identify the possibility of data fabrication through experimental instrument and data consistency comparison; and it can identify potential image forgery or beautification issues in the paper by combining image processing.