2226 results about "Image conversion" patented technology

The invention provides a talent evaluation management method and system based on AI intelligence, and relates to the technical field of artificial intelligence analysis, and the method comprises the steps: S1, converting a handwritten resume image into structured text data through OCR image recognition; converting the interview record into a dialogue text with a time sequence mark through voice transfer; performing format analysis on the electronic document to extract original text content; performing coding standardization processing on the structured text data, the dialogue text and the original text content to generate a standardized text data set containing semantic tags; and S2, performing context semantic coding on the standardized text data set, performing node alignment and semantic disambiguation processing on professional terms through a domain knowledge graph, and generating a text feature vector containing an entity association relationship. According to the method, through multi-source data integration, semantic deep analysis and dynamic matching calibration, the talent ability is accurately evaluated, the result is scientific and quantitative, and intelligent and interpretable talent evaluation and decision support is provided.

The invention relates to the technical field of membrane material image processing, in particular to a membrane material surface treatment defect detection method and system based on image recognition, and the method comprises the following steps: collecting a membrane material surface image, carrying out the statistics of the frequency of gray levels in a gray level image, and obtaining the gray level distribution information of the membrane material surface image; and dividing the membrane material surface image into a plurality of local areas with the same size, calculating a gray level distribution entropy value in each local area, and generating a membrane material surface local area analysis result. According to the method, the membrane material surface image is converted into the gray level image, the gray level frequency is counted, fine gray level distribution information is obtained, preliminary region division of the surface image is achieved, and the positioning accuracy of potential defects is improved. The gray level distribution entropy value of the local area is used as a defect evaluation index, and a potential defect area is accurately marked by combining a preset distribution threshold value, so that the sensitivity of defect detection is effectively improved.

The invention discloses a thermal imaging temperature rise trend early warning system based on time-space sequence prediction, and particularly relates to the technical field of thermal imaging data prediction and early warning. The thermal imaging temperature rise trend early warning system comprises an image conversion module, a fluctuation feature extraction module, an edge prediction module, an anomaly characterization module and a prediction decision module; a temperature dynamic change rate and gradient intensity are calculated, edge model prediction is carried out based on a fluctuation index combination, when the fluctuation index combination does not exceed a stable interval, a lightweight deep network model deployed at a thermal imaging acquisition end is called, and when the fluctuation index combination exceeds the stable interval, a prediction decision module determines whether to switch to a high-order multi-modal model; the space-time information extraction capability is improved by constructing the temperature evolution data body, the prediction path is dynamically controlled based on the fluctuation index combination, and the prediction stability and efficiency are improved; and the abnormal activation index and the prediction offset index are combined to realize adaptive switching of model calling, so that the accuracy and adaptability of the early warning system are enhanced.

Disclosed in the present invention are a hyperspectral calculation imaging method and system based on multi-domain fusion of spatial, spectral and frequency domains, and a medium. The method of the present invention comprises: using a two-dimensional offline discrete cosine transform (DCT) to convert an RGB image Y into a frequency domain to obtain a frequency domain feature map Yfreq; extracting a frequency information image (I) from the frequency domain feature map Yfreq; using a two-dimensional offline inverse discrete cosine transform (IDCT) to transform the frequency information image (I) into a spatial domain to obtain a frequency information image Xfreq of the spatial domain; and fusing the frequency information image Xfreq of the spatial domain into the spatial-spectral domain features of the RGB image Y to generate a hyperspectral image (II). The present invention aims to solve the problems of poor detail information and low reconstruction accuracy of hyperspectral images in existing hyperspectral calculation imaging, and realizes high-fidelity reconstruction of a target spectrum.

The invention provides a multi-modal intelligent question-answering and recommendation system supporting emotional speech output, and relates to the technical field of visual question-answering, and the system specifically comprises a multi-modal question-answering module, a multi-modal recommendation module, a speech recognition module, and a speech synthesis module. Wherein the multi-mode question answering module converts an image input by a user into a natural language form, and final question answering is completed in combination with a comet knowledge base COMET; the voice recognition module is used for recognizing voice data input into the multi-mode intelligent question answering and recommending system and processing the voice data into a text form; the multi-modal recommendation module identifies whether modal missing exists in input data or not, generates representation of the missing modal, obtains vector representation of the user and the article through a graph convolutional neural network and learning according to an interaction matrix of the user and the article, carries out reliability calculation, and finally sends a multi-modal recommendation result to the user and the article. Sending back to the multi-mode question and answer module; and the voice synthesis module outputs the voice to the user.

The invention discloses an image recognition system based on machine vision, which comprises a deep learning model, and is characterized in that an image recognition module comprises an image data sensing module for receiving and processing original image data, capturing an image from a camera or an image file, and performing preliminary format conversion and preprocessing; the image feature extraction module is used for converting the image into a form which can be understood by a machine based on a convolutional neural network; the online learning framework is used for dynamically adjusting model parameters according to data input in real time; the environment adaptability adjusting module is used for dynamically adjusting image processing parameters, changing a feature extraction weight, adjusting a learning rate and adjusting an identification strategy according to environment changes; the recognition and classification module is used for executing object recognition and classification tasks based on the extracted features and the learned model; the parameter mapping unit is used for mapping the environment parameters to specific parameter adjustment of the model; and the environment adaptability development unit is used for extracting useful information from the environment data and converting the useful information into an instruction of an adaptability adjustment strategy.

The invention relates to the technical field of panoramic video processing, in particular to a multi-modal fusion panoramic video intelligent content analysis method, which comprises the following steps of: acquiring a panoramic video frame and a synchronous audio thereof; performing spherical projection transformation on the panoramic image data, and converting the equidistant projection image into a spherical image; generating a plurality of plane images based on the spherical image; performing candidate target position detection based on the plurality of plane images; based on a candidate target position detection result, an image target detection model is utilized to realize instance segmentation of a target, and target features are extracted to generate a target embedded description vector sequence; based on the synchronous audio, an audio recognition processing module is used for carrying out time sequence information extraction, and an acoustic attention sequence is formed; a spectrum sensor is adopted to realize association fusion of the target embedded description vector sequence and the acoustic attention sequence, and an audio and video collaborative attention sequence is generated; and based on the audio and video collaborative attention sequence, establishing an audio and visual event identification model, and obtaining event content described by the panoramic content.

The invention relates to a river water ecological space global monitoring method and system, and the method comprises the steps: recognizing and segmenting a water body image from an RGB image photographed by an unmanned plane based on a U-Net deep learning model, and forming a water body recognition image; converting and reconstructing the RGB image aerially photographed by the unmanned aerial vehicle into a water body hyperspectral image based on a hyperspectral information continuation reconstruction model; the U-Net deep learning model extracts a multispectral segment sequence of pixel points of a water body in the water body hyperspectral image and sends the multispectral segment sequence to the classification regression model; and calculating the multispectral segment sequence based on a classification regression model so as to label a concentration classification result of chlorophyll a in a water body hyperspectral image, thereby realizing visualization of chlorophyll concentration. The method gets rid of limitation of technical means and time acquisition of hyperspectral data acquisition, and realizes the effect of acquiring river global images at any time and at any moment.

The invention discloses an immersive space virtual-real interaction method and system, and relates to the technical field of virtual reality interaction, and the method comprises the steps: collecting a full-view scene picture and illumination data through a camera, carrying out the preprocessing, simulating the real optical characteristics according to the scene picture and illumination data, and building a virtual scene; the virtual scene is evaluated and optimized; acquiring a user gesture image for analysis, identifying a user interaction command for virtual scene interaction, and displaying an interaction result in real time; and recording and storing the user interaction command and the interaction result. According to the method, the trueness and quality of the virtual scene are effectively improved, meanwhile, the user interaction command is recognized and analyzed by collecting the user gesture image and converting the user gesture image into the three-dimensional coordinate for virtual scene interaction, the gesture recognition accuracy is improved, and the experience effect of user virtual scene interaction is greatly improved.

The invention provides a CT (Computed Tomography) image super-resolution reconstruction method based on a generative adversarial network. The method comprises the following steps of: 1, collecting high-resolution image data and corresponding low-resolution image data; 2, establishing a CycleGAN model comprising a first generator, a second generator, a first discriminator and a second discriminator; a third step of training a CycleGAN model by using the collected high-resolution image data and the corresponding low-resolution image data so as to optimize parameters of the CycleGAN model; and a fourth step of performing image conversion on the to-be-enhanced medical image which is input into the trained CycleGAN model.

Disclosed is a method for training a diffusion model for image-to-image translation, which is performed by a computing device. The method may include: obtaining an image of a target domain; sampling random noise from a distribution of a source domain; and training a diffusion model that translates an image of the source domain to the image of the target domain based on the sampled noise.

The invention discloses a large model defense method based on multi-view image-text conversion, and relates to the technical field of artificial intelligence security. The method comprises the steps of obtaining an image-text dialogue prompt word text, extracting syntactic structure parameters and semantic parameters of statements, splicing the syntactic structure parameters and the semantic parameters into a multi-modal tensor, and expanding a spliced vector into a plurality of structure vectors according to semantic relationship density to form a semantic structure vector group. According to the method, semantic density splitting and image space mapping of the multi-modal tensor are utilized, the cross-modal correlation analysis capability is enhanced, the image-text mixed attack path is accurately identified, and the entity mapping relation between the pixel gradient and the regional mask is combined, so that two-way verification of image-text semantic consistency is realized, and semantic fault vulnerabilities of single-modal detection are eliminated; a path intensity and instruction word dynamic weight fusion mechanism is adopted, the abnormal risk level of a statement structure is quantified, the adaptive limitation of a static rule to semantic variation is broken through, and the illegal content output probability is reduced.

The invention provides a fault diagnosis method based on multi-modal multi-scale feature fusion, and the method comprises the steps: collecting signal sources when faults occur at different positions of an aero-engine bearing through a sensor, the signal sources including but not limited to vibration signals, sound signals, temperature, humidity and current; performing unified de-noising processing on the vibration signal to obtain an initial one-dimensional signal X0; performing one-dimensional feature extraction on the initial one-dimensional signal X0 through an MCNN module; performing image conversion on the initial one-dimensional signal X0 to obtain an initial two-dimensional image T1, and performing two-dimensional feature extraction on the initial two-dimensional image T1; fusing the extracted one-dimensional features with the extracted two-dimensional features to generate a multi-modal feature H1; and inputting the fused multi-modal feature H1 into an LSTM network for fault diagnosis and classification. According to the method, the fused multi-modal features are input into the LSTM classification module for fault diagnosis and classification, so that fault detection of the aero-engine bearing is realized.

The invention discloses a crack detection method and system based on digital twinning and multiple intelligent perception, and the method comprises the steps: S100, installing a track, an X-shaped support frame, an IMU unit and an industrial camera, and collecting the image data of a detected bridge; s200, calling an industrial camera to realize training of crack detection; s300, performing comprehensive scanning and three-dimensional model modeling on the tested bridge to obtain initial point cloud data of the tested bridge; s400, setting an inspection path and speed, and dynamically detecting the bridge crack; s500, when a crack is detected, adjusting the position of the industrial camera for continuous detection; s600, performing micro motion enhancement by using phase information between adjacent images, and converting the acquired crack continuous image into a video; s700, splitting the video frame by frame into enhanced images, and performing three-dimensional model reconstruction on cracks; s800, obtaining crack data at each moment; and S900, detecting environmental data at the crack in real time, and carrying out early warning on bridge safety. And rapid and comprehensive data acquisition and crack monitoring are realized.

The invention discloses a multimedia image optimization method and system, and relates to the technical field of image optimization, and the method comprises the steps: obtaining a to-be-optimized multimedia image, carrying out the HSI color space conversion, extracting a brightness component in an HSI color space, and carrying out the brightness enhancement; the contrast ratio of the enhanced brightness component is adjusted, and brightness area division and dynamic range optimization are carried out; and carrying out edge enhancement on the optimized brightness component, recombining to generate an enhanced HSI image, and converting the enhanced HSI image back to the RGB color space to obtain an optimized multimedia image. According to the method, the brightness, the contrast ratio and the details of the image are comprehensively optimized, the brightness layering sense is improved, the problem that the details of the image in highlight and dark areas are lost is solved, the marginal definition and the color fidelity of the image are improved, the visual quality of the multimedia image can be remarkably improved, and the actual application requirements of multiple scenes are met.

The invention relates to the technical field of image conversion, and discloses a multi-view conversion method based on a multi-view consistency diffusion model, and the multi-view consistency diffusion model is trained through a unified multi-view-to-multi-view conversion framework based on the diffusion model. The conversion framework has a new self-supervised training strategy and a consistency and antagonism supervision strategy, and the strategies utilize an existing 2D single-view image converter and a 3D Gaussian splash technology to generate pseudo-truth values as supervision signals, so that view consistency and high-frequency details are enhanced; the multi-view consistency diffusion model trained by the conversion framework further comprises a potential multi-view consistency module, and the potential 3DGS module is used as a 3D representation of a bottom layer to promote information exchange across multiple views, so that 3D priori is introduced into the diffusion model to ensure view consistency. Finally, a joint optimization strategy is provided, and better balance between consistency and authenticity can be realized.

The invention relates to an underwater low-illumination image enhancement method based on local color correction and a multi-scale variation decomposition model, and belongs to the technical field of image processing. The method comprises the following steps: firstly, performing color correction on an input underwater low-illumination image; next, the corrected image is converted from an RGB color space to an HSV color space, a multi-scale variational decomposition model is applied to a V channel in the image, and a base layer, two detail layers and an atomization layer are generated; then, the atomization layer is separated, self-adaptive brightness equalization is carried out on the base layer, an enhanced base layer is obtained, self-adaptive detail sharpening is carried out on the detail layer, and an enhanced detail layer is obtained; and finally, linearly fusing the enhanced base layer and detail layer to obtain an optimized V channel, converting the image back to an RGB color space, and outputting an enhanced underwater image. According to the method, the overall enhancement of the image is realized, the contrast, the brightness and the detail expression are remarkably optimized, and the visual effect of the underwater image is remarkably improved.

A small pressurized water reactor fault diagnosis method based on a CNN-LSTM hybrid network comprises the following steps: firstly, acquiring sensor signals in a pressurized water reactor control system under a normal working condition, introducing corresponding faults at different positions according to characteristics of various typical faults, and acquiring corresponding sensor signals under different working conditions; discrete sampling processing is carried out as a training set and a test set; preprocessing the fault training set by adopting a signal-image conversion method, inputting obtained image data into a CNN-LSTM diagnosis model and training, and then verifying the diagnosis accuracy and robustness of the model based on test set data; parameters in the diagnosis model are continuously adjusted, so that an optimal diagnosis model is obtained; according to the technical means of combining the CNN network for extracting image features and the LSTM for extracting time sequence data fault features, the defects of a traditional fault diagnosis method in the aspects of diagnosis efficiency, accuracy, effect and the like are overcome; the invention further comprises a system, equipment and a storage medium for implementing the method.

The invention provides a mathematical problem solving method and device based on a multi-modal large model and electronic equipment, and relates to the technical field of artificial intelligence. The method comprises the following steps: determining a mathematical element image of a mathematical problem; inputting the mathematical element image into an image coding model to obtain an image vector output by the image coding model; the image coding model is obtained by training based on a sample mathematical element image and a positive sample text description and a negative sample text description corresponding to the sample mathematical element image; inputting the image vector into a self-adaptive module to obtain an image conversion coding vector output by the self-adaptive module; the adaptive module is obtained based on training of a sample image vector and a sample text vector; determining question stem characters of the mathematical question, and inputting the question stem characters and the image conversion coding vector into the large language model to obtain a prediction answering process output by the large language model; the large language model is obtained based on sample question stem characters, sample image conversion coding vectors and sample answering process training, and the mathematical problem solving capability of the multi-modal large model can be improved.

The invention provides a low-illumination image enhancement method, and belongs to the technical field of image processing. The method comprises the following steps: converting an original RGB image into an HSV color space to obtain a chroma channel component, a saturation channel component and a brightness channel component; enhancing the saturation channel component and the brightness channel component to obtain a saturation channel enhanced component and a brightness channel enhanced component; fusing the saturation channel enhancement component, the brightness channel enhancement component and the chroma channel component to obtain a synthesized RGB image; and performing noise reduction processing on the synthesized RGB image to obtain an enhanced RGB image. Through the method provided by the invention, the brightness balance, the detail retention degree and the color naturalness of the output image are remarkably improved; therefore, the problems of overexposure, noise amplification, detail loss and the like which are easily caused by unbalanced brightness distribution under low illumination are solved.

The invention relates to the technical field of image optimization, and discloses an image lossless fusion method and system based on depth feature extraction, and the method comprises the following steps: collecting multi-modal input data from different sensors, carrying out the preprocessing of each modal in the multi-modal input data, and carrying out the preprocessing of each modal in the multi-modal input data; the multi-modal input data comprises a visible light image, an infrared image and a depth map, a multi-layer pulse neural network is used for simulating pulse emission characteristics of biological neurons, time sequence feature extraction is performed on the multi-modal input data, and feature representations of different levels are captured. According to the method, deep feature extraction is carried out through the SNN algorithm to carry out image fusion, the problems of feature mutual exclusion and modal conflict when infrared and visible light images are processed through a traditional method can be effectively solved, a concrete image can be converted into an abstract feature, and then the abstract feature is converted into an end-to-end conversion process of the fused image. And the real-time and fidelity requirements in a dynamic scene are met.

A natural language test case for an application is automatically converted into a test script by a test script generator. During the generation of the test script, the test script generator may access a blueprint of the application. The blueprint may include a time-evolving model of the application, which may include a set of translations and a state machine model of the application. The state machine model may include a state space and a set of state transitions. During the test script generation process, the blueprint may be continually updated to include new knowledge of the application. The test script generator may communicate with an artificial intelligence (AI) engine in order to determine the semantic similarity between two phrases, convert images into textual description, and perform tasks requiring the use of a large language model (LLM).

The invention relates to the technical field of image conversion, and provides a bidirectional fusion image style migration method and system based on content and style decoupling, and the method comprises the steps: obtaining a style image set and a content image, respectively extracting a common style feature and a content feature, carrying out the bidirectional fusion of the style feature and the content feature through a cross attention mechanism, and carrying out the bidirectional fusion of the style feature and the content feature. Generating two-way fusion features after fusion; extracting a text feature based on the obtained text description, splicing the text feature with the bidirectional fusion feature to generate a condition control vector as guide information for image generation, executing a denoising inverse diffusion process guided by the condition control vector on the obtained target image, and finally decoding to obtain a stylized image; based on bidirectional feature fusion of styles and contents and a text-guided diffusion generation mechanism, an image style migration effect with delicate style expression, clear semantic structure and strong controllability is realized.

The invention discloses a universal multi-modal target tracking method based on space-time propagation and modal cooperation, and belongs to the technical field of computer vision. The method comprises the following steps: converting RGB and X modal images into a token form, and constructing initial features in combination with modal specific time tokens; the method comprises the following steps of: extracting a multi-level enhanced feature through a Transform encoder and a Mama collaborative prompt block; generating discriminative fusion features by using a gating fusion and context sensing module; a time-guided attention mechanism is adopted to strengthen search area features, and a result is output through a tracking prediction head; and transmitting the fusion time token as historical information to the next frame, and dynamically updating the template by combining a long-short time template updating strategy. According to the method, complementarity and space-time dependence between modes are effectively mined, tracking robustness and generalization ability in a complex scene are improved, and the method is suitable for various mode combination tasks such as RGB-D, RGB-T and RGB-E.

The present invention provides a bridge crack detection method, system and storage medium based on the YOLO algorithm, which relates to the technical field of bridge crack detection. The specific steps include: S1. collecting images of bridge crack areas, converting them into grayscale images and using the YOLO algorithm for detection, dividing the cracks into corresponding grid units, drawing crack boundary boxes and saving images of the boundary boxes; S2. determining the four boundaries of the boundary box according to its center coordinates, width and height, and determining the positional relationship between the cracks and the boundary box; S3. determining the number and size of the cracks according to the positional relationship, and drawing a new crack boundary box; S4. calculating the total density and total area of ​​the cracks in the grid unit, and obtaining the comprehensive coefficient of the cracks; S5. comparing the comprehensive coefficient with a preset threshold value to determine the severity of the cracks. The present invention realizes refined crack area detection, and also significantly improves the detection accuracy and adaptability of cracks.

The invention discloses a low-grade highway construction quality intelligent detection method and system, and relates to the technical field of highway engineering detection, and the method comprises the steps: collecting an RGB image, converting the RGB image into a gray-scale map, and calculating a flatness feature value through a flatness feature fusion method; calculating a gap characteristic coefficient based on the flatness characteristic value, and calculating an edge disorder index by using an accumulation method; and evaluating a construction quality score based on the gap feature coefficient and the edge disorder index, and constructing a visual interface to display the construction quality score. The method comprises the following steps: collecting an RGB image, converting the RGB image into a grey-scale map, and calculating a flatness characteristic value by using a flatness characteristic fusion method; calculating a gap characteristic coefficient, and calculating an edge disorder index by using an accumulation method; the construction quality score is evaluated, the limitation of a single characteristic index is avoided, the efficiency and precision of pavement quality detection are improved, and the robustness and adaptability of detection are enhanced.

The invention discloses a mask generation and image decoupling diffusion three-dimensional medical image generation method, relates to the technical field of image processing and analysis, and solves the problems of poor generalization ability, low calculation efficiency and high dependence on training data during image conversion in the prior art. The method comprises the following steps: acquiring a mask image, and processing the mask image by using a multi-condition diffusion probability model to obtain a multi-label mask sequence; screening the three-dimensional medical image data according to a screening condition, determining an informed slice set, and inputting the multi-label mask sequence and the informed slice set into a volume diffusion generation model to obtain a three-dimensional composite image; random noise is added to the three-dimensional composite image, a diffusion semantic refinement generation model is utilized, the three-dimensional composite image added with the random noise is refined, and a refined three-dimensional image is obtained; according to the invention, data decoupling and model generation volume consistency are realized, and a three-dimensional medical image with higher quality can be generated.

Here provides a system, apparatus, and method(s) for processing images based on colour constancy. The method comprises obtaining an image in a first colour space; converting the image to data in a second colour space; transforming the data using chromatic adaptation; performing a first normalisation on the transformed data, where the first normalisation comprises applying a dynamic spatial filtering technique to adjust the transformed data based on light intensity; applying a set of filters to the normalised data, where the set of filters is convoluted based on the normalised data in relation to the image; performing a second normalisation on the filtered data to obtain an illumination estimation of the image in relation to the filtered data; and outputting the normalised data from the second normalisation, where the normalised data maintains colour constancy based on the illumination estimation, removing the illumination from the normalised data.

The invention provides a method for generating multi-dimensional landform vector data based on remote sensing image semantic segmentation, and belongs to the technical field of remote sensing image ground object recognition and artificial intelligence, and the method comprises the steps: training a landform recognition deep learning model based on a remote sensing image, adjusting a pre-training weight to optimize an image encoder, and generating a classification result; the landform recognition deep learning model comprises an encoder formed by a multi-layer convolutional network and a decoder of an up-sampling and feature fusion architecture; extracting a single-band label corresponding to each landform type from the classification result, and generating a binary raster image with the single-band labels; and converting the binary raster image with the single-band label into a vector diagram, and combining the vector diagram with the elevation information to generate multi-dimensional geographic data.

The invention discloses an image-text question and answer method and device based on a multi-modal large model and a thinking chain and a medium, belongs to the technical field of natural language processing, and aims to solve the technical problem of how to improve the reasoning ability, the answer accuracy and the interpretability in a complex image-text question and answer task. According to the technical scheme, the method comprises the steps of collecting an image and a question text related to the image; the method comprises the following steps of: preprocessing an image, and converting the preprocessed image into an image token sequence imgtoken through a pre-trained image encoder ViT; the method comprises the following steps: preprocessing a question text related to an image, encoding the preprocessed question text, and converting the preprocessed question text into a question text token sequence; and splicing the image token sequence imgtoken and the question text token sequence query token into a multi-modal input representation.