90 results about "Discrete cosine transforms" patented technology

A system and method for compressing synthetic aperture radar (SAR) images with enhanced phase recovery and unwrapping capabilities is disclosed. The system performs preprocessing on input SAR images, applies discrete cosine transform (DCT) to create subbands, and utilizes a multi-pass amplitude compression technique. A specialized neural network performs phase unwrapping using compressed amplitude information and interferogram wrapped phase data. The system employs a channel-wise transformer fusion block (CTFB) for feature fusion and a multi-stage context recovery subsystem with optimized loss functions for both amplitude and phase recovery. The method achieves improved compression efficiency and phase recovery accuracy, particularly beneficial for Interferometric SAR (InSAR) applications.

The invention discloses an electronic document tracing method and device based on dynamic encryption and multi-modal watermarking, and relates to the technical field of information security and digital rights management. The method comprises the following steps: acquiring a PDF document uploaded by a user, encrypting the PDF document by adopting a randomly generated main encryption key, and acquiring and storing the encrypted PDF document; the content of the encrypted PDF document is analyzed, secret information is embedded into a picture in the document based on a two-dimensional discrete cosine transform algorithm, and picture watermark embedding is completed; a self-adaptive watermark embedding algorithm is adopted to embed secret information into a text in the document, and text watermark embedding is completed; related information of the checking operation is written into a block chain database; dynamically extracting watermark information from the divulged PDF document by adopting a watermark extraction algorithm; and querying a traceability database according to the extracted watermark information, and outputting a traceability result by comparing the extracted watermark information with information in a database storing various watermark information. According to the invention, the survival rate and the concealment of the watermark can be improved.

The invention provides a high-fidelity anti-compression image watermarking method and system based on spectrum-airspace decoupling, and belongs to the field of information security. Firstly, the watermark information is mapped and remodeled; a watermark encoder based on multi-granularity spectrum-spatial domain feature decoupling is constructed, discrete cosine transform is introduced to filter out high-frequency components, Haar wavelet transform is adopted to realize lossless downsampling, a fast Fourier transform dynamic filter is combined to capture global semantic features, and local texture details are combined through multi-scale spatial domain volume accumulation; designing a physical perception and visual self-adaptive dual embedding strategy, and anchoring watermark energy to an anti-compression brightness channel; constructing an anti-attack layer containing differentiable JPEG compression simulation and mixed noise simulation, and participating in network training; and constructing a decoder and designing a loss function to carry out network optimization. According to the method, the robustness of the watermark under strong compression and complex black box attacks is improved, and extremely high visual imperceptibility is realized through physical and visual constraints.

For compressing synthetic aperture radar (SAR) images, preprocessing operations are performed on an input SAR image. A discrete cosine transform is performed on the image, and multiple subbands are created, where each subband represents a particular range of frequencies. The subbands are organized into multiple groups, where the multiple groups comprise a first low frequency group, a second low frequency group, and a high frequency group. A latent space representation is generated corresponding to each of the multiple groups of subbands. A first bitstream is created based on the latent space representation, and an alternate representation of the latent space is used for creating a second bitstream, enabling multiple-pass techniques for SAR image data compression, including phase unwrapping for supporting interferometric SAR (InSAR) applications.

The invention discloses a fresh tea leaf sorting method based on a frequency domain tree topology network, computer equipment and a storage medium. The method covers the complete process of image acquisition, preprocessing, frequency domain decomposition, deep modeling, map construction and classification. Firstly, image quality is improved through color normalization and edge enhancement, and frequency domain tree decomposition is carried out through wavelet transform and discrete cosine transform to extract multi-scale features. And then, fusing long and short range dependent modeling and a residual convolution module to realize multi-level feature representation, and constructing a tree topology attention path and a structure map for simulating a bud-leaf-vein relationship to enhance semantic understanding. A tree structure is adopted to perceive a classification function, and fine-grained classification of single bud, one bud and one leaf, one bud and two leaves and one bud and multiple leaves is achieved. In training, the robustness of the model is improved by combining cross entropy loss, data enhancement and a regularization strategy. The method is high in classification accuracy and good in stability on a plurality of tea image data sets, and the practical level of automatic fresh tea leaf sorting is effectively improved.

The invention discloses an urban water supply prediction method based on a non-stationary perceptual Transform-BiLSTM model, and the method comprises the steps: independently calculating the mean value and variance of each sequence sample as non-stationary statistical information through introducing a reversible normalization mechanism, enabling a sequence to depend on weight learning reversible mapping on the basis of maintaining the original distribution characteristics of data, and carrying out the calculation of the mean value and variance of each sequence sample as the non-stationary statistical information; and the perception capability of non-stationary components is enhanced, and the training stability is improved. In addition, discrete cosine transform (DCT) is adopted for frequency domain modeling, and the feature extraction capacity of the model for the periodicity and trend of the urban water supply sequence is enhanced. In the aspect of feature modeling, the model fuses the global attention mechanism of Transform and the time sequence modeling capability of BiLSTM, cooperatively captures the long-term dependency relationship and local time sequence dependency features in urban water supply data, and has a remarkable capturing capability effect on the change of a non-stationary structure under the background of multi-scale fluctuation of an urban water supply sequence.

A size of a transform block is identified. A transform type for the transform block is identified. The transform type includes a horizontal transform type and a vertical transform type. Identifying the transform type includes determining whether the size of the transform block is below a predefined block size; and, in response to determining that the size is below the predefined block size, selecting a default transform type for each of the horizontal transform type and the vertical transform type. The transform type is then applied to the transform block. The default transform type can be the discrete cosine transform (DCT).

The invention belongs to the field of computer vision and artificial intelligence, and particularly discloses a human body three-dimensional posture estimation method and system based on Transform and a graph convolutional network, and the method comprises the steps: firstly receiving a two-dimensional skeleton sequence, sampling a center sub-sequence, and converting the two-dimensional skeleton sequence and the center sub-sequence into an initial spatial-temporal feature containing a spatial position code; through a double-flow parallel space coding module, global dependency features are obtained through a Transform encoder, and local connection features are obtained through a graph convolutional network encoder (based on a human skeleton topological adjacent matrix); discrete cosine transformation is carried out on the complete sequence to obtain a low-frequency coefficient, and frequency domain features are generated; and after the three types of features are spliced, deep fusion is carried out through a time-frequency fusion Transform encoder, and finally, the three-dimensional attitude of the target frame is output through a regression head. The method gives consideration to both efficiency and precision, is high in robustness, and is small in calculation cost increase.

The invention discloses a transient thermal field inversion method and system based on deep learning, and the method comprises the steps: firstly obtaining thermal field evolution data and space grid coordinates of a measured object in a cooling process, and then designing a thermal field evolution network model composed of two sub-networks, the second sub-network outputs a deduced evolution thermal field, and deduces real material parameters of an object based on a finite difference deep learning model through joint optimization and fusion of internal and boundary thermal evolution equations as physical constraints so as to improve precision and robustness; on the basis, a time-containing inversion operator model is constructed, discrete cosine transform is utilized to map a thermal diffusion coefficient, a time step size and a final-state temperature field evolution sequence to a frequency domain, and accurate reasoning of an initial temperature field is realized through iterative optimization of an operator learning framework. The method has a good application prospect in material science and engineering detection, and can effectively assist in analysis and prediction of a complex heat conduction process.

An image compression device includes a discrete cosine transform (DCT) circuit, a quantization noise shaping (QNS) circuit, and an encoder circuit. The DCT circuit performs a DCT on original image data to generate first data. The QNS circuit performs QNS on block data in first data to determine, based on a first coefficient and a second coefficient of the block data, a QNS score of the first coefficient, and replace the first coefficient with the second coefficient when the QNS score is greater than zero so as to generate second data, wherein the second coefficient is obtained by decreasing an absolute value of the first coefficient. The encoder circuit encodes the second data to generate compressed image data.

The invention provides a light-weight pedestrian motion prediction method based on a mask, and is suitable for the technical field of human-computer interaction. According to the method, human body 3D skeleton point data is processed through space and time masks, key features are extracted by using a local perceptron constructed by a lightweight multilayer perceptron module and a cross-frame fusion device, the features are fused by using 1 * 1 convolution and splicing technologies, then a frequency-space domain pedestrian prediction action sequence is generated through a prediction module, and the frequency-space domain pedestrian prediction action sequence is obtained. And converting into a time-space domain sequence through an inverse discrete cosine converter. The method has the advantages of light model, quick response and suitability for real-time interaction. In addition, the strategy of gradually increasing the number of training frames improves the accuracy and stability of prediction.

The invention discloses a human eye fixation point prediction method based on a deep convolutional network and frequency domain feature enhancement, and the method comprises the steps: employing the deep convolutional network (namely a residual network ResNet) as a backbone network to form an encoder branch, and employing five layers of coding blocks to extract the spatial features of five layers of an input image; the five layers of spatial features extracted by the encoder are respectively sent to a frequency domain feature enhancement module for frequency domain feature enhancement based on discrete cosine transform (DCT) so as to enhance the features of each layer of human eye fixation area and reduce interference features; sending the frequency-domain-enhanced characteristics of each level into a decoding block of a corresponding layer of a decoder branch, and carrying out decoding and spatial up-sampling operation in sequence from a high layer to a low layer; and the output of the last decoding block of the decoder branch is subjected to 1 * 1 convolution and double up-sampling to obtain a human eye fixation point prediction result. According to the method, frequency domain feature enhancement and sequential decoding from a high layer to a low layer are carried out on the spatial multi-layer convolution features extracted by the backbone network, so that the human eye fixation point prediction precision is improved.

A method for disparity estimation between digital images includes generating an interleaved image from two or more digital images with an offset between them, where the interleaved image is subdivided into a plurality of patches, computing discrete cosine transform (DCT) coefficients of each of the plurality of patches, computing, for each of the plurality of patches, a mean DCT descriptor from the DCT coefficients of each patch, and determining a disparity map from the mean DCT descriptor of each of the plurality of patches using a classifier. The disparity map is configured for real-time depth estimation from the two or more digital images.

The invention relates to the technical field of part identification, and discloses a part identification method and device based on an industrial large model, and the method comprises the steps: carrying out the image block division and embedded transformation of an original image of an industrial part, obtaining a first Token sequence, carrying out the two-dimensional discrete cosine transformation of the first Token sequence, and obtaining a second Token sequence; fusing the second Token sequence with a plurality of prototype feature vectors selected from a category prototype memory library to obtain a memory guide vector; performing gating modulation and residual connection processing on the second Token sequence based on the memory guide vector to obtain a third Token sequence; and performing iterative refinement on the third Token sequence to obtain a fourth Token sequence, and performing global pooling and classification prediction on the fourth Token sequence to obtain a category identification result of the industrial parts, thereby enhancing the discrimination of the part characteristics, and effectively solving the technical problem of difficult identification of small samples of rare parts.

A method for decoding a video includes determining, from multiple sets of multiple transform selection candidates, one set of multiple transform selection candidates based on at least one of a number of non-zero coefficients in a current block and a position of a last non-zero coefficient in the current block. The method for decoding the video also includes selecting one inverse transform method based on the one set of multiple transform selection candidates. The method for decoding the video further includes generating a residual block of the current block by performing the one inverse transform method on coefficients of the current block, where the multiple sets of multiple transform selection candidates have one or more candidates that correspond to a non-Discrete Cosine Transform 2 (non-DCT 2) inverse transform method.

The invention provides a rapid detection method and system for parasites in fresh food, and the method comprises the steps: collecting a multispectral image of the fresh food, selecting near-infrared and green light channels, calculating a normalized differential value, generating a parasite stress feature map, and calculating the global variance of the feature map; edge texture features are extracted through a Laplacian operator, and the original spectrogram and the two feature maps are stacked and input into a deep network; the network intermediate layer divides the features into a core group and an auxiliary group, the core group generates a channel vector, and the auxiliary group performs discrete cosine transform compression according to global variance; splicing the compression feature and the core feature to obtain a depth feature vector; meanwhile, carrying out weighted fusion on the multispectral image by utilizing a channel vector, calculating a gradient covariance matrix and flattening the gradient covariance matrix to obtain a spectral statistical vector; and splicing the depth features and the spectral statistical vectors, outputting a detection score through a classifier, and comparing the detection score with a threshold value to obtain a detection conclusion.

The application relates to a multispectral and panchromatic image fusion spatial quality evaluation method based on a region convolution network, which improves the processing process of a fused image and a panchromatic image in a traditional region-based multispectral image and panchromatic image fusion spatial quality evaluation method. The spatial features of region images in the original fused image and the panchromatic image are directly extracted by using a GoogLeNet network, instead of performing gray image conversion and discrete cosine transformation on the fused image. The spatial information loss of the image is effectively avoided, and meanwhile, the deep features with stronger representation ability and generalization ability are extracted, so that the spatial quality of a fusion result is evaluated at a feature level. Finally, an intuitive spatial quality distribution map is obtained to represent the spatial quality of local regions of the fusion result.

This invention relates to the field of image recognition, specifically to an automated tunnel construction monitoring system based on image data. The system includes an edge computing node that acquires the original tunnel image and constructs an atmospheric scattering physical model using measured data from an optical dust concentration sensor. The edge computing node transforms the original image to the frequency domain, extracts low-frequency brightness features and high-frequency texture features using discrete cosine transform, and adaptively compensates the high-frequency texture features with weights based on the transmittance matrix calculated by the physical model to suppress diffuse light interference. The compensated features are then input into a lightweight convolutional neural network via inverse transform. This scheme introduces dust physical parameters as prior constraints into the frequency domain feature weight calculation, reducing the probability of image edge artifacts and color distortion under conditions of localized strong light and high dust, ensuring the physical authenticity of target edge features in the reconstructed image, and improving the accuracy of feature extraction under harsh conditions.

A network level adaptive based lightweight feature map compression method, in the forward inference process of a convolutional neural network, when the intermediate feature map output by the activation function needs to be exchanged between the calculation unit and the off-chip memory due to the limited on-chip storage resource, the intermediate feature map is first compressed, that is, the network shallow layer feature map is subjected to transform domain processing by using integer discrete cosine transform, the network deep layer feature map is subjected to block maximum value extraction processing, then unified quantization processing and entropy coding processing are performed, the compressed feature map is written into the off-chip memory, so as to reduce the data size, thereby reducing the off-chip storage access bandwidth requirement and data carrying energy consumption. The present application is a feature map compression method which does not depend on neural network retraining, can fully utilize the spatial correlation of shallow layer feature map, has low calculation complexity and good hardware implementation characteristics, so as to significantly reduce the storage and energy consumption overhead in the inference process of the convolutional neural network under the premise of ensuring the inference accuracy.

A System / Method / Device for segmenting the choroid-scleral layer from an optical coherent tomography (OCT) volume scan. The present system uses a deep learning machine model based on a neural network that include multiple convolution layers, but no deconvolution layers. Rather, the present neural network is based on a novel architecture based on the discrete cosine transform.

The invention relates to a three-dimensional reconstruction method based on DCT (Discrete Cosine Transform) decoding. The method comprises the following steps: projecting a four-step phase shift stripe of a specific code to an object and collecting a deformed stripe; calculating a wrapped phase; the key improvement lies in that after a least square unwrapping model is constructed, improved divergence calculation based on a cosine function is adopted, nonlinear transformation is carried out on a multi-direction wrapped phase gradient so as to suppress noise errors, and an improved divergence field is generated; secondly, performing two-dimensional DCT (Discrete Cosine Transform) forward transformation on the divergence field, and solving an absolute phase field through inverse transformation after operation with a transfer function in a frequency domain; and finally completing three-dimensional reconstruction. The system comprises a projection module, an acquisition module and a processing module. According to the method, non-linear divergence calculation is introduced to be combined with DCT frequency domain solving, the defect that a traditional method is sensitive to noise is effectively overcome, and the reconstruction speed and robustness are improved while precision is guaranteed.

The application relates to the technical field of visual text tamper detection, and specifically discloses an open set visual text tamper detection method based on sparse constraint rectified flow, which comprises the following steps: acquiring a real image and constructing training data; constructing a neural network, including a multi-modal forensic tokenizer, an F-DiT encoder and an F-DiT decoder; wherein the multi-modal forensic tokenizer extracts RGB visual block features, spatial rich model filtering features and block discrete cosine transform frequency domain features from an image state, and fuses the features to obtain a multi-modal forensic information feature vector; the neural network is trained by using the training data to obtain a forensic feature network; a query image is acquired, the forensic feature network is used to predict a recovery velocity vector field, a pixel-level tamper probability graph is calculated according to the recovery velocity vector field, and tamper area positioning is realized. The application can realize high-precision positioning of unknown open set text tampering without supervised paired data.

The invention provides an oil-immersed transformer fault decision-making method and system based on a three-dimensional voiceprint map, and the method comprises the steps: collecting a voiceprint signal of a transformer body through a high-sampling-rate microphone array which is arranged in a standardized manner; an optimized decoding process based on improved inverse discrete cosine transform is innovatively adopted to construct a three-dimensional voiceprint map matrix containing time, frequency and sound intensity information, and the limitation of traditional single feature analysis is broken through; space-time alignment and fusion are carried out on the voiceprint map, the real-time load rate, the oil temperature and other multi-physical field data, a unified high-dimensional feature vector is constructed, and efficient processing and feature mining are carried out on the high-dimensional data through a light-weight sliding window feature extraction mechanism of depth separable convolution reconstruction. More sensitive and robust online diagnosis of early abnormal states and composite faults is realized, and model complexity and calculation burden are remarkably reduced through deep adaptation of a core algorithm and a hardware architecture.

The application provides a traffic hub vertical field large model training and light deployment method and system, relates to the technical field of machine learning, and comprises the following steps: collecting traffic hub multi-scene service corpus, marking static knowledge, semi-static knowledge, periodic knowledge and dynamic knowledge into four categories according to knowledge timeliness, and constructing a classification data set; performing discrete cosine transform mapping on the weight increment of a pre-trained large language model to a frequency domain space, dividing four frequency band intervals according to the timeliness category, retaining sparse coefficients in each frequency band as trainable parameters, and adopting a differentiated learning rate to fine-tune a teacher model; transferring the teacher model capability to a light student model through progressive three-stage distillation; deploying the student model to a mobile terminal, establishing an end-cloud collaborative mechanism, and updating parameters according to a frequency band level strategy; and responding to user dialogue requests based on the deployed model. The application drives frequency domain sparse distribution according to knowledge timeliness, realizes ultra-low parameter fine-tuning and mobile terminal light deployment.

The invention discloses a large model attack defense method based on FGSM attack and DCT-IDCT (discrete cosine transform-inverse discrete cosine transform) denoising, relates to the field of large model attack defense, and comprises FGSM attack and DCT-IDCT denoising technologies. According to the method, an image denoising defense strategy based on FGSM attack and DCT-IDCT transformation is designed, a new solution thought is provided for safety application of the deep learning technology, safety deployment of deep learning in various fields is promoted, compared with a traditional FGM algorithm, the FGSM algorithm is adopted in the project, the calculation efficiency is remarkably improved through the selection, and the method is suitable for being applied to the deep learning technology. And time resources are saved. According to the FGSM algorithm, a countermeasure sample is generated by rapidly calculating a gradient symbol, so that the attack process is more efficient, and meanwhile, convenience is provided for design and implementation of a defense strategy.

The invention discloses a pavement crack segmentation method based on lightweight DCT frequency domain modeling, and the method comprises the steps: constructing a lightweight segmentation backbone network, which comprises a LiteResStage coding module composed of point convolution and depth separable convolution, and is used for efficiently extracting multi-scale structural features; a frequency domain-space collaborative fusion module (SAFM) is designed, discrete cosine transform (DCT) is executed on high-level features to obtain frequency domain structure components, response in the main direction of a crack is enhanced through directional perception frequency domain convolution (AFC), and meanwhile the identification degree of a local edge area is improved in combination with a space attention mechanism; fine reconstruction of a crack area is realized by adopting step-by-step up-sampling and cross-layer feature fusion of a lightweight decoder. According to the method, the parameter quantity and the calculation quantity are remarkably reduced, meanwhile, the crack structure continuous modeling capacity and the weak texture area recognition precision are improved, and high-precision and low-delay crack segmentation can be achieved in scenes such as road inspection, intelligent traffic and vehicle-mounted terminals.

The application discloses an adversarial sample generation method based on AdvDrop, relates to the technical field of machine learning security, and processes two different branches of an image input space domain and a frequency domain; for the frequency domain attack AdvDrop, first, the input image is segmented into N*N blocks, and discrete cosine transform (DCT) is used on each block to convert them to the frequency domain; a quantization matrix M is introduced to reduce some specific frequencies of the transformed image; a tangent function is introduced in the quantization process to gradually approach the quantization function, and then the quantization matrix M is accurately adjusted through the new quantization function; then, the image is converted from the frequency domain to the space domain through inverse discrete cosine transform (IDCT) operation; finally, the space domain attack and the frequency domain attack fusion module are used to iteratively update the adversarial perturbation by using the gradients from different fields, and the adversarial sample is generated; the quality of the generated adversarial sample is improved, the difference between the distribution characteristics of the adversarial sample and the distribution characteristics of the real sample is reduced, and the attack success rate is improved.

This invention proposes a multi-granular joint representation method for learners' higher-order thinking in online collaborative inquiry scenarios, belonging to the field of online learning and intelligent education. This method integrates multi-source data such as learner profiles, behavioral sequences, and collaborative discourse to construct a joint embedding space. It then uses a pre-trained language model to extract shared semantic features, achieving a unified representation of higher-order thinking. Discrete cosine transform (DCT) is introduced for frequency domain analysis, and the compression ratio is adaptively determined by the power spectrum concentration, reducing the computational complexity to O(N log N). A progressive block-based strategy is employed to extract fine, medium, and coarse-grained semantic features, and multi-layer integration is achieved through upsampling and weighted fusion. Simultaneously, a frequency-domain constrained label relationship modeling mechanism is introduced to strengthen the semantic matching of features with higher-order cognitive dimensions such as analysis, evaluation, and creation, providing technical support for personalized learning diagnosis and precise intervention.

Example techniques and devices for coding media data are described. An example device for encoding media data includes one or more memories configured to store the media data and one or more processors implemented in circuitry and coupled to the one or more memories. The one or more processors are configured to determine a hyperprior variable of a neural video coder based on the media data. The one or more processors are configured to apply a discrete cosine transform (DCT) to the hyperprior variable to generate DCT coefficients and encode the DCT coefficients.

The application discloses a high-efficiency compressed sensing target recognition system and method based on discrete cosine transform, and belongs to the technical field of computer vision.The application decomposes the separable characteristic of the discrete cosine transform into sequentially executed row direction one-dimensional discrete cosine transform and column direction one-dimensional discrete cosine transform, and then directly outputs the discrete cosine transform coefficient by using programmable resistance or capacitance to form a corresponding hardware circuit, and a special neural network model for directly completing an image recognition task in a frequency domain is designed, so that the image is not restored from the frequency domain to a pixel space domain by inverse discrete cosine transform, but target recognition is directly performed by using the frequency domain feature, so that redundant calculation links are eliminated, and the overall calculation amount is reduced by about 1 / 3; through software and hardware collaborative optimization, the application can be deployed on a resource-limited edge device, has low delay and meets the real-time requirement, and can help the development of the Internet of Things, automatic driving and other fields.