12 results about "Copy detection" patented technology

The invention discloses a distributed image quality inspection system based on artificial intelligence, and belongs to the technical field of image quality inspection. A preprocessing module; the multi-expert AI model cluster is used for executing at least one analysis of copying detection, door head similarity comparison, OCR (Optical Character Recognition) field extraction, bar code recognition and date detection; the consistency verification module is used for receiving an output result of the multi-expert AI model cluster and carrying out cross validation and contradiction analysis in a unified decision-making space so as to identify a complex collaborative fraud mode; the adaptive learning module comprises an adversarial sample perceptron and an incremental learning engine, the adversarial sample perceptron is used for finding a new abnormal mode from the rejected task in a clustering manner, and the incremental learning engine is used for carrying out periodic incremental updating on the multi-expert AI model by utilizing the found abnormal mode; and a quality inspection rule engine. According to the invention, the efficiency and the automation level of large-scale image quality inspection are improved.

The present disclosure relates generally to signal encoding for value documents. One aspect of the technology relates to authentication of value documents comprising line art patterns. In one example, authentication relies of detection of signals encoded within the line art, and expected frequency domain analysis of the line art. Other combinations are described as well. For example, authentication may rely on detection of signals encoded within encoded and then printed documents, expected frequency domain characteristics encoded signals, presence or absence of halftoning, a color check and / or trained classifier analysis. Other aspects, technology, claims and combinations are described as well.

This invention provides a method, apparatus, electronic device, and storage medium for detecting image copying, belonging to the field of artificial intelligence technology. The method includes: inputting the image to be identified into a feature extraction model to obtain multi-dimensional image visual features; if the multi-dimensional image visual features meet preset copying judgment conditions, then inputting the multi-dimensional image visual features into an image detection model to obtain a copying detection result; the image detection model includes a rule encoding network, a cross-modal fusion network, and an output network; the rule encoding network encodes the copying image judgment rules to generate a rule condition vector; the cross-modal fusion network fuses the rule condition vector and the multi-dimensional image visual features to generate fused features; and the output network determines the copying detection result based on the fused features. This invention achieves targeted capture of copying features by encoding the copying judgment rules into vectors and fusing them with visual features across modalities, thereby improving the accuracy of copying recognition and robustness against complex copying methods.

The invention provides a picture copying detection method and device, electronic equipment and a storage medium, and belongs to the technical field of artificial intelligence, and the method comprises the steps: inputting a to-be-recognized picture into a feature extraction model, and obtaining a multi-dimensional image visual feature; if the multi-dimensional image visual features meet a preset copying judgment condition, inputting the multi-dimensional image visual features into an image detection model, and obtaining a copying detection result; the image detection model comprises a rule coding network, a cross-modal fusion network and an output network; the rule encoding network encodes the duplicated picture judgment rule to generate a rule condition vector; the cross-modal fusion network carries out fusion processing on the rule condition vectors and the multi-dimensional image visual features to generate fusion features; and the output network determines a copying detection result based on the fusion features. According to the method, the copying judgment rule is coded into the vector, and cross-modal fusion is performed on the vector and the visual features, so that targeted capture of the copying features is realized, and the accuracy of copying recognition and the robustness of complex copying means are improved.

The present disclosure relates generally to signal encoding for value documents. One aspect of the technology relates to authentication of value documents comprising line art patterns. In one example, authentication relies of detection of signals encoded within the line art, and expected frequency domain analysis of the line art. Other combinations are described as well. For example, authentication may rely on detection of signals encoded within encoded and then printed documents, expected frequency domain characteristics encoded signals, presence or absence of halftoning, a color check and / or trained classifier analysis. Other aspects, technology, claims and combinations are described as well.

The present disclosure relates generally to signal encoding for value documents. One aspect of the technology relates to authentication of value documents comprising line art patterns. In one example, authentication relies of detection of signals encoded within the line art, and expected frequency domain analysis of the line art. Other combinations are described as well. For example, authentication may rely on detection of signals encoded within encoded and then printed documents, expected frequency domain characteristics encoded signals, presence or absence of halftoning, a color check and / or trained classifier analysis. Other aspects, technology, claims and combinations are described as well.

Disclosed in the embodiments of the present application are an audio copy detection method and apparatus, and a device, a storage medium and a program product. The method comprises: extracting a global audio feature corresponding to audio to be processed, and extracting an audio segment feature sequence corresponding to the audio to be processed; retrieving from an audio retrieval library an approximate global audio feature corresponding to the global audio feature; acquiring an audio segment feature sequence corresponding to target audio to which the approximate global audio feature belongs, and on the basis of the audio segment feature sequences respectively corresponding to the audio to be processed and the target audio, determining an audio similarity between the audio to be processed and the target audio; and if the audio similarity reaches a preset similarity or greater, determining the target audio as copy audio corresponding to the audio to be processed.

The invention discloses a software copy detection method and device, a medium and a product. The method comprises the following steps: acquiring static characteristic data of target software, and determining declaration identity information according to the static characteristic data; when the target software runs, collecting dynamic behavior data, and obtaining network communication data; according to the declaration identity information, a behavior baseline is matched and copied from a baseline library; comparing the dynamic behavior data with a genuine behavior baseline to obtain a deviation value, and generating a behavior deviation record when the deviation value is greater than or equal to a deviation threshold value; analyzing the network communication data, and when the network communication data meets a preset network exception condition, generating a network exception record; fusing the behavior deviation record and the network exception record to generate a risk score of the target software; and generating a detection result and a disposal instruction according to the risk score and a preset disposal strategy. By implementing the technical scheme provided by the invention, the accuracy and robustness of software compliance judgment are improved, and the missing detection risk caused by feature counterfeiting is reduced.

An event detection device (100) according to an embodiment of the present invention comprises: an event storage unit (121) that records event information composed of combinations of a plurality of objects to be operated associated with object screen information and a plurality of operation types; an event detection unit (111) that acquires an operation log including at least the objects to be operated and the operation types, and the event information to compare the operation log with the event information and detect / determine the event corresponding to the operation log; a copy destination candidate extraction unit (112) that, if the detected / determined event is file copying, acquires a copy source file, and, from the operation log immediately before copy detection, acquires a copy destination folder name to execute a search using the folder name, and extract, as copy destination candidate files, all of the files in a folder obtained as the result of the search; and a copy destination estimation unit (113) that calculates the degree of similarity between the copy source file and the plurality of copy destination candidate files to determine, as the copy destination file, the copy destination candidate file having the highest degree of similarity to the copy source file.

A method based on multi-copy generation, multi-copy detection and multi-copy sequencing and used for improving the accuracy of genetic detection.

The invention belongs to the technical field of graphic image processing, and discloses a document image copying detection method based on chromaticity and frequency domain feature fusion, which comprises the following steps: acquiring a document image to be copied and detected; extracting local chromaticity features from the text region / edge region of the document image; domain change processing is carried out on the document image, selective enhancement is carried out on a moire spectrum peak in a frequency domain, phase and pixel alignment is kept, and frequency domain enhancement features are extracted; and fusing the local chromaticity feature and the frequency domain enhancement feature, performing copying judgment based on the fused feature, and outputting a copying detection result of the document image. According to the method, the local chrominance features and the discriminative frequency domain features are extracted, and stable discrimination performance under different display screen types and document templates can be realized by utilizing the mutually complementary characteristics of the two types of features in the spatial domain and the frequency domain, so that the precision and robustness of document image copying detection are effectively improved.

The application discloses a target detection model training method and device, a target detection method and device, equipment and a medium, and relates to the technical field of target detection. The method comprises the following steps: acquiring an image set, wherein the image set comprises a plurality of first sample images; determining a detection region comprising a detection object in the first sample image, intercepting an image in the detection region, and obtaining a second sample image; copying the detection object in the second sample image, and pasting the copied detection object in the second sample image according to a preset constraint condition; determining target position information of the detection object in the second sample image; and training a target detection model according to the second sample image and the target position information of the detection object in the second sample image. The embodiment optimizes small target detection in terms of super-resolution of the image and diversity of the training sample, narrows the detection range, effectively reduces the false positive rate, and improves the accuracy of the model.