505 results about "Product image" patented technology

The invention discloses an industrial image anomaly detection method and device, equipment and a storage medium, and relates to the field of image recognition. Obtaining a defect-free product graph, making a comparison data set based on the defect-free product graph, and performing pre-storage processing; performing feature point shape matching on the comparison data set based on the received to-be-detected image and the extracted feature point data, and determining a comparison image of the to-be-detected image; taking the to-be-detected image as a target object, correcting a product image area in the image, and aligning the product image area with the product image area of the to-be-detected image according to a pixel shift operation; and comparing the aligned product image areas, and identifying abnormal defects in the to-be-detected image. According to the scheme, the comparison data set of the defect-free product image is constructed, the feature point matching and pixel-level alignment technologies are combined, the problem of false detection caused by product position deviation or form change in a traditional method is effectively solved, the adaptability to illumination change is improved through brightness adjustment and difference matrix analysis, and the detection accuracy is improved. The method has the advantages of high detection precision, high environmental adaptability and high processing efficiency.

The invention specifically relates to the technical field of intelligent control, and discloses an intelligent control-based mold forming optimization system, which comprises a defective finished product image acquisition module, a defect intelligent identification module, a defect score quantification module, a process parameter synchronous acquisition module, a process risk dynamic analysis module and a process association closed-loop optimization module, the method comprises the following steps of: calculating a single-parameter risk index and a comprehensive risk index based on a process risk dynamic analysis module through a process parameter synchronous acquisition module in real time of full-flow process parameters of an injection molding process, identifying abnormity when the parameters deviate from an optimal target value, immediately triggering early warning, quickly positioning core cause parameters through a defect-process incidence matrix, and quickly positioning the core cause parameters through the defect-process incidence matrix. The influence of adjustment of different parameters on comprehensive defect scores is simulated within an equipment constraint range through a reverse optimization algorithm, a reverse optimization scheme is generated, a full-link traceable data link is formed through timestamps, stop loss time and production cost are greatly reduced, and accurate assessment and prediction of risks are achieved.

The invention relates to the technical field of industrial manufacturing digital management, in particular to a machine vision production line performance evaluation and optimization management system, which comprises a data acquisition module for triggering a high-speed industrial camera array, a vibration sensor and an RFID reader through a central synchronous controller to synchronously acquire product images, equipment operation and material circulation data; the data processing and fusion module extracts product quality features based on CNN, and fuses multi-modal data through time sequence alignment normalization and an attention mechanism; the dynamic efficiency evaluation module calculates OEE, FPY and a production line balance rate in real time by means of a deep neural network; the optimization strategy generation module is used for reinforcing the learning agent to output optimization instructions such as equipment parameter adjustment; and the control execution module converts the instruction into an industrial protocol format, issues the instruction to the PLC, and verifies the effect to form a closed loop. According to the method, the data relevance and the evaluation real-time performance are improved, the dynamic state of the adaptive production line is optimized, and the efficiency improvement is facilitated.

The invention belongs to the technical field of precision marketing and intelligent recommendation, and discloses a B2B customer deep insight and precision reaching method based on a multi-modal large model, and the method comprises the specific steps: S1, carrying out the fusion and deep analysis of multi-modal data; s2, performing customer multi-dimensional preference modeling; s3, an intention and emotion analysis engine; s4, generating a personalized marketing strategy; s5, recommendation execution and verbal skill optimization; s6, feedback collection and reward function drive optimization; and S7, applying a cold start solution and transfer learning. According to the invention, through integration of multi-mode data of client official websites, news information, social media dynamics, mail communication, product images and conference recording, panoramic insight of clients from a business level to behavior details is realized; in combination with deep analysis of a pre-trained large model on texts, images and audios, explicit demands can be obtained, and industry features, cultural characteristics and potential concerns of customers can be understood.

The invention relates to a layout image generation method and device, computer equipment and a storage medium, and the method comprises the following steps: carrying out the element analysis of original image data, and obtaining image element information; performing feature extraction on the image element information to obtain image features and text features; performing hypergraph structure construction according to a preset design rule, the image features, the text features and the image element information to obtain hypergraph structure information; performing style parameter adjustment and coordinate adjustment on the hypergraph structure information according to the matching similarity corresponding to the element embedding vector to obtain to-be-rendered information; and performing image layout rendering according to the to-be-rendered information to obtain an effective layout image. The method can be applied to application scenes of financial science and technology and digital medical systems, and insurance product propaganda images or disease prevention propaganda images which effectively express image elements and features can be effectively, accurately and quickly generated according to original insurance product images or health education images in the system.

The invention relates to the technical field of cocktails, discloses a cocktail formula retrieval enhanced generation method based on multi-modal feature fusion, and aims to solve the problems of poor accuracy and low individuation degree of an existing method. The scheme mainly comprises the steps that a cocktail finished product image and an ingredient constraint condition text uploaded by a user side are acquired; visual feature extraction and semantic feature extraction are carried out, fusion coding is carried out, and a unified query vector is generated; searching candidate formulas with similarity scores Top-K from a pre-constructed cocktail formula knowledge base; and inputting the query vector and the candidate formula into a retrieval enhanced generation model, generating a cocktail formula recommendation result including a formula name, main ingredients, alternative ingredient suggestions, making steps, formula difficulty and estimated making time, and returning the cocktail formula recommendation result to a user side for display. According to the method, the accuracy and the individuation degree of cocktail formula retrieval are improved, and the method is suitable for intelligent bartending, catering training and personal customization service scenes.

The invention relates to the field of industrial defect detection, in particular to an industrial defect detection self-supervised segmentation method for iterative pseudo label refinement, which comprises the following steps of: constructing a system comprising a strategy model, a refinement model, a reward model and a meta-learning training module; inputting the multi-modal data into the strategy model, and outputting a rough defect mask; based on the rough defect mask, prompting refinement is carried out through a refinement model, and a refinement mask is output; based on the refinement mask, the to-be-detected product image, the standard template image, the depth image and the infrared image, calculating a comprehensive quality score through a reward model, and screening high-quality samples with qualified scores; and updating a preset training data set based on the high-quality sample, performing supervised training on the strategy model by using the updated training data set, and repeating the steps to form an iterative loop. By constructing a self-supervised closed loop, a system can be driven to autonomously learn defect features from an unlabeled production line multi-modal image only by a small amount of initial reference data.

Disclosed herein is a system and method of identifying products on a retail shelf using a feature extractor trained to extract features from images of products on the shelf and output identifying information regarding the product in the product image. The extracted features are compared to extracted features in a feature gallery library and a best fit match is obtained. A product ID is then assigned to the image of the product and the assigned product ID is validated by matching the product ID with product identifying information extracted from a shelf label associated with the image of the product.

The invention provides a printing quality detection method and system, a medium and a product, and relates to the technical field of printing. The method comprises the following steps: establishing a corresponding relation between a target printing result and an actual printing result by acquiring standard image data and printed finished product image data; dividing image data by using a region recognition model, extracting key regions (such as characters, complex patterns and color transition contents) and non-key regions (such as pure color, background and blank contents), and ensuring that pixel coordinate ranges of the key regions and the non-key regions are in one-to-one correspondence; and further calculating the similarity between the key area and the non-key area through a printing similarity matching model, and carrying out weighted calculation to obtain the comprehensive similarity. And finally, accurately judging whether the printing quality is qualified or not by comparing the comprehensive similarity with a preset threshold value. The high-precision and differentiated detection of the printing quality is realized, and the accuracy, objectivity and efficiency of the printing quality detection are improved.

The invention relates to an industrial quality inspection data cooperative transmission method driven by image recognition, in particular to the field of artificial intelligence, which analyzes video frames in real time through a lightweight neural network, accurately locates and extracts key areas and features in industrial product images, constructs a dynamic semantic scene graph to understand contents and divide priorities, and improves the quality inspection efficiency. The core of the method is that non-uniform intelligent coding is carried out on video streams according to semantic importance of contents, high-fidelity transmission of key information such as defects is ensured, non-key areas are greatly compressed to save bandwidth, scheduling is carried out in the transmission process according to priorities, confidence feedback based on a cloud recognition result is introduced, closed-loop control is formed, and high-fidelity transmission is realized. According to the method, the front-end analysis model, the coding strategy and the network path are adaptively optimized, so that low-delay and high-reliability visual quality inspection data transmission and accurate identification can be continuously and stably realized in a complex industrial network environment, and the overall efficiency and the intelligent level of online quality inspection are remarkably improved.

The invention discloses an industrial product defect credible detection method based on evidence Transform and double-branch Query decoupling, and the method comprises the steps: obtaining a defect sample training data set which comprises an industrial product image and a corresponding defect type and position mark; based on the defect sample training data set, constructing an uncertainty perception defect detection model; training the uncertainty perception defect detection model by using the total loss function; and acquiring a defect sample test data set, inputting a test image into the trained uncertainty perception defect detection model, and outputting a detection result including defect categories, bounding box positions and uncertainty evaluation. According to the method, a double-branch Query decoder architecture is adopted, the problem of optimization conflict caused by task coupling in a traditional detection model is effectively solved, and the reliability of industrial defect detection and the credibility of decision making are remarkably improved.

The invention provides a defect detection method and device for improving a YOLO model based on an attention mechanism. The method provided by the invention comprises the following steps: acquiring image data of a to-be-detected industrial product; the improved YOLOv10 model performs feature extraction, multi-scale feature fusion and defect positioning identification on the industrial product image data to obtain a defect detection result of the industrial product; wherein the SE module is used for strengthening a channel dependency relationship and detail representation of local detail features, and the CBAM module is used for modeling channel attention and space attention on global semantic features; the bridging layer controls middle and low layer features and high layer features to keep uniform channel dimension and spatial resolution by adjusting the size and stride of a convolution kernel; introducing a 1 * 1 convolutional layer after Concat operation of multi-scale feature fusion, and performing channel compression, linear fusion and semantic alignment on multi-scale fusion features; and constructing a loss function fusing the GHM loss and the dynamic IoU loss.

The invention discloses a category price-based hot competitive product mining method for AI intelligent marketing, and relates to the technical field of marketing, and the method comprises the following steps: building a unified time base line, extracting a continuous sales volume curve of commodities under a target category, calculating the instantaneous slope of sales volume change in the sales volume curve, and calculating the instantaneous slope of the sales volume change; based on the sudden change interval of the instantaneous slope, determining a candidate region of short-period sales volume increase; and constructing a causal factor set in the candidate region, and mapping the channel expansion track and the promotion track to a sales volume curve point by point. According to the method, through the joint constraint of the causal residual and the user behavior density tensor, the sales volume anomaly weight index is generated and written back to the competitive product portrait, false sales volume signals are effectively filtered, and the accuracy of competitive product identification and marketing decision is improved. And meanwhile, short-time Fourier transform is introduced to decompose a sales volume curve, high-frequency abnormity is dynamically weakened by using a spectral domain attenuation coefficient, and a hot sell weight is ensured to truly reflect a long-term and periodic trend, so that the reliability and the analysis precision of a competitive product portrait are enhanced.

The invention discloses a multi-stage attention and generative adversarial network collaborative product generation method and system, and relates to the technical field of image generation, and the method comprises the steps: obtaining a low-resolution clothing image, focusing the low-resolution clothing image on a clothing image key region through a multi-stage attention mechanism, and carrying out the image refining processing through combining text features, a high-resolution clothing image is obtained; processing the text description to obtain corresponding word features, processing the high-resolution clothing image obtained by processing the multi-stage attention generative adversarial network to obtain corresponding local image features, and inputting the word features and the local image features into a deep attention multi-modal similarity model to obtain a deep attention multi-modal similarity model; outputting and obtaining the fine-grained similarity loss of the image and the text; and optimizing a pre-constructed multi-stage attention generative adversarial network based on the adversarial loss and the fine-grained similarity loss of the image and the text, and generating a product image based on the optimized multi-stage attention generative adversarial network.

The invention belongs to the technical field of computer vision, and discloses an interactive semi-automatic anomaly detection labeling method, system and device and a medium, and the method comprises the steps: obtaining a to-be-detected image of an industrial product, manual click input representing an abnormal region position, and natural language description of a defect type; based on the defect-free image reference set, extracting position constraint features of each image patch of the to-be-detected image, and calculating pixel-level position rapid abnormal residual features; converting the natural language description into a discriminant language feature vector by using a pre-training language model and a discriminant encoder; processing the residual feature through a residual feature branch, and generating a first fusion feature through a cross-modal attention mechanism under the guidance of a language feature vector; processing the original pixel information by combining the pixel information branch with click input to generate a second fusion feature; and fusing the two features and decoding to obtain a pixel-level abnormal annotation mask, thereby realizing high-precision semi-automatic annotation of the abnormal region in the industrial product image.

The invention belongs to the technical field of cultural IP derivative generation, and particularly relates to a rapid generation system and method for customizable cultural IP derivatives. Aiming at the existing problems that end-to-end automatic generation from a voice instruction to a printable derivative cannot be realized, semantic coordination and style consistency processing between multiple IP roles and a scene is lacked, and a user cannot be supported to carry out independent interaction and joint editing on multiple roles and accessories in multiple display areas, the following scheme is provided. The system comprises terminal equipment, a local server and a cloud server. According to the invention, end-to-end automatic generation from a voice instruction to a cultural IP derivative image can be realized; a plurality of IP roles and target scenes can be processed at the same time, and semantic coordination and style unification are achieved; and a user is supported to carry out real-time personalized adjustment on roles, accessories and colors, and finally high-quality cultural IP derivative images with consistent styles and coordinated illumination are generated.

The invention discloses an automatic defect detection method and system based on cross-resolution and multi-level knowledge distillation. The method comprises the following steps: step 1, acquiring an image of an intelligent manufacturing product to be detected; 2, constructing a teacher-student network distillation model for intelligent manufacturing defect detection; 3, training the teacher network model in the step 2 by using the data set obtained in the step 1; 4, training a student network model in the teacher-student network distillation model in a cross-resolution and multi-level manner; and step 5, utilizing the trained student network model to carry out defect detection on a to-be-detected intelligent manufacturing product image. A cross-resolution and multi-level knowledge distillation framework is provided, and a collaborative distillation mechanism of local details and a spatial structure is designed; a morphological self-adaptive semantic distillation method is provided, and the method can be better suitable for dynamic and real-time defect detection of intelligent manufacturing products.

The invention discloses a product image recognition method, device and equipment, a medium and a product, and relates to the technical field of artificial intelligence, and the method comprises the steps: obtaining a first multispectral image of a first product object, and carrying out the dynamic noise suppression and feature enhancement processing of the first multispectral image, and obtaining a second multispectral image; inputting the second multispectral image into a pre-trained image recognition model to obtain a defect probability thermodynamic diagram corresponding to pixel points in the first multispectral image and uncertainty confidence of defect positioning; determining a defect type and defect position information corresponding to the first multispectral image according to the defect probability thermodynamic diagram and the uncertainty confidence; wherein the image recognition model comprises a global feature extraction module based on a Vision Transform architecture and a local feature extraction module based on a dilated convolutional neural network. According to the technical scheme provided by the embodiment of the invention, the identification capability of sub-pixel-level microdefects can be improved, and the accuracy of a product image identification result is improved.

To enable a viewer of an appraisal result to easily understand grounds for determination of authenticity of an appraisal item.SOLUTION: According to one embodiment, an appraisal system includes: an appraisal unit for appraising whether an appraisal item matches a registered item on the basis of a registered item image registered in advance and an appraisal item image captured by a user; an image generation unit for generating at least one of a matching-point image indicating matching points between the registered item image and the appraisal item image and a non-matching-point image indicating non-matching points between the registered item image and the appraisal item image; and a display unit for displaying the result of the appraisal and at least one of the matching-point image and the non-matching-point image.SELECTED DRAWING: Figure 12

The invention provides a defect detection method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring a template image and a product image of a to-be-detected product; performing feature matching on the template image and the product image, and performing non-rigid alignment on the product image based on feature point pairs obtained by feature matching to obtain an alignment image of which the geometric view angle is consistent with that of the template image; and defect detection is carried out based on the aligned image and the template image to obtain a detection result, so that the problem of image deformation caused by the fact that the surface of the to-be-detected product is a curved surface and the shooting angle is not correct in a traditional scheme is effectively solved, and local and global deformation of the product image can be corrected, thereby greatly improving the alignment precision of defect detection, and improving the detection accuracy of the to-be-detected product. Therefore, the real difference of the product surface can be more focused during defect detection, non-defect geometric deformation interference is effectively shielded, and the accuracy and robustness of defect detection of complex surfaces of household electrical appliances and the like are greatly improved.

The invention discloses a lifting frame control method and system capable of intelligently recognizing lifting points, and aims to solve the problems that traditional lifting operation depends on manpower, efficiency is low, and high-altitude operation risks exist. The core of the method is that automatic identification and accurate positioning of the lifting point are realized through combination of machine vision and automatic control. The system is composed of a PLC master control system, an industrial camera, a walking trolley, a servo motor and the like. The PLC acquires a product image through a camera, performs feature matching with a pre-stored template (by adopting ORB, RANSAC and other algorithms), and calls a successfully matched lifting point formula to drive the walking trolley to move; and if no matching template exists, calculating the position of the lifting point in real time based on image pixel coordinates and camera calibration parameters. In the downward moving process of the hanging bracket, fine adjustment and safety confirmation are achieved through a sensor contact signal, and finally hanging connection and hoisting are automatically completed. Full-process automation is achieved, manual climbing is thoroughly avoided, and operation safety and efficiency are greatly improved.

Image rendering techniques for use with virtual worlds and interactive media are described herein. Techniques may include: acquiring a first scene depth texture map and a first scene color texture map of a first image frame; acquiring, based on the first scene depth texture map, a first spatial position of a vertex of a target triangle face in a first clipping space; mapping, based on a first camera parameter and a second camera parameter, the first spatial position to a second spatial position in a second clipping space; generating a second scene depth texture map and a second scene color texture map based on the second spatial position and the first scene color texture map; and displaying a second image frame based on the second scene depth texture map and the second scene color texture map. Image display frame rates for a virtual scene may be improved, thereby improving visual effects.

The invention belongs to the technical field of industrial visual inspection, and discloses a PLC visual inspection linkage control method and system based on AI image recognition. The method comprises the steps of automatically adjusting exposure parameters of a camera based on an evaluation result of real-time brightness and contrast of an industrial product image to be detected, and obtaining a corrected industrial product image; extracting an illumination invariant feature from the corrected industrial product image, and generating an illumination invariant feature vector; inputting the original image of the same industrial product image to be detected and the corresponding illumination invariant feature vector into a pre-trained feature optimization model, and outputting an optimized illumination invariant feature vector; inputting the industrial product images shot under different exposure conditions into a pre-trained neural network model for fusion to obtain a shared feature vector; the problem of missing detection and false detection caused by illumination change in high-speed production of a traditional visual algorithm is solved.

The invention provides an intelligent robot feeding method and system, and relates to the technical field of humanoid robots, and the method comprises the steps: obtaining a test rubber product image; determining a plurality of initial stress points of the tested rubber product by using an initial stress point model based on the tested rubber product image; determining three-finger stress points based on the plurality of initial stress points of the tested rubber product; generating a plurality of sets of grabbing schemes based on a plurality of initial stress points and three-finger stress points of the tested rubber product, wherein each set of grabbing scheme comprises five-finger stress points; acquiring a captured video of each set of capturing scheme; target grabbing points of the remaining two fingers are determined based on the grabbing video of each set of grabbing scheme; and based on the force bearing points of the three fingers and the target grabbing points of the remaining two fingers, the five-finger robot is controlled to conduct feeding grabbing on the remaining rubber products. According to the method, the adaptive grabbing points of the rubber products can be efficiently and accurately determined, and stable feeding grabbing of the robot is achieved.

The invention relates to the technical field of machine vision, in particular to a contact lens printing pattern defect detection method and system based on a multi-scale fusion feature, and aims at each new pattern, only dozens of frames of qualified product images need to be input for training, and the detection efficiency is improved. And the limitation of the current method when the current method is adaptive to various patterns and weak flaws are detected can be made up. The semi-supervised deep learning method can break through the dependence of traditional deep learning on large-scale labeled data, utilizes a semi-supervised learning strategy to mine potential information in unlabeled data, improves the recognition capability of a model on complex and sparse defects, and meanwhile, aims at the characteristics of a color mold transfer printing pattern, and improves the recognition efficiency of the color mold transfer printing pattern. A targeted deep learning network structure and a loss function are designed, and the sensitivity and generalization ability of the model to specific defect types are ensured.

The invention discloses a parameter control method, device and equipment for an injection molding machine and a storage medium, and relates to the technical field of injection molding machine parameter control. The method comprises the following steps: firstly, acquiring surrounding environment temperature, material melt index and viscosity of the injection molding machine, determining three types of environment temperature adjustment amounts in combination with corresponding reference thresholds, and performing weighted correction to obtain a target environment temperature and performing control; meanwhile, pressure and flow velocity adjustment amount is determined according to the melt index and viscosity, the initial pressure and flow velocity are subjected to weighted correction to obtain second pressure and flow velocity, the injection molding pressure is controlled by combining the equipment health degree index, and compensation adjustment amount is calculated when the health degree is insufficient to obtain third pressure through weighted correction. In combination with product image detection, the flow velocity is corrected according to a notch or burr type first defect value to obtain a third flow velocity, and the pressure maintaining duration is corrected according to a surface depression type second defect value to obtain a second pressure maintaining duration; the defective rate is counted through preset duration, when the defective rate reaches the standard, the parameter optimization coefficient is adjusted according to the decreasing amplitude and the threshold value, and each weight is dynamically optimized. The method improves the product quality.

Methods, computer systems, computer storage media, and graphical user interfaces are provided for facilitating generation of brand-aligned product images. In one implementation, a product-environment prompt including a text description of a reference image is obtained. Further, a set of image features extracted from the reference image is obtained. Thereafter, a brand-aligned product image is generated by performing outpainting from a product representation in accordance with the product-environment prompt and the set of image features extracted from the reference image. The brand-aligned product image can then be provided for display via a graphical user interface.

The invention discloses an image recognition and classification system and method based on machine learning, and relates to the field of industrial image processing, and the method comprises the steps: collecting image data of an industrial product, and marking related information; the method comprises the following steps: detecting an acquired industrial product image through a self-adaptive method, removing noise in the image, and classifying industrial product materials based on feature extraction; dynamically adjusting the weight of a defect detection task by sharing a CNN backbone network according to the importance of a product type; constructing a multi-task model to evaluate the severity of the defect; constructing a physical parameter calculation function, setting a score by combining a multi-task model output result, performing weighted fusion on the function and the model result, and classifying the severity of product defects according to a fusion result; through adaptive noise removal and material classification, adaptability to a complex industrial environment is enhanced, and through combination of a multi-task model and physical parameters, comprehensive evaluation of defects from multiple dimensions is realized, and classification precision is improved.

The invention provides an e-commerce commodity graph differentiation generation method and device, equipment and a medium, and the method comprises the steps: obtaining an original to-be-shelved commodity graph of e-commerce, and finally obtaining the disassembly information; the method comprises the following steps: adjusting an original commodity image into 980 * 980 pixels, performing Gaussian blur processing at the same time, and then converting image pixel data into a Base64 coded character string; constructing a composite cue word according to the image data, the disassembly information and a format required by generation; inputting the composite cue word into a model to generate a new scene description; inputting the new scene description, the original commodity graph and the synthesis requirement into a model to generate a synthesis cue word, and then inputting the original commodity and the synthesis cue word into an image-text model to generate a differentiated commodity graph; setting the output resolution, the number of iterations and the learning rate of the SuperIR model, and inputting the differentiated commodity graph into the SuperIR model to generate a differentiated commodity optimization graph; the defects of low efficiency, poor scene adaptation, main body distortion and difficulty in repeated avoidance of a traditional method are overcome.

A classification model generating system includes: an obtainer that obtains a good product image group including a plurality of good product images; a defective portion image generator that generates a plurality of defective portion images, based on a seed image group obtained by geometrically transforming a seed image simulating a defective portion, the seed image being an artificially drawn image; a combination processing unit that combines each of the plurality of defective portion images with the good product image group to generate a defective product image group; and a classification model generator that performs classification training by using a part of the good product image group and a part of the defective product image group as a training image group to generate a classification model.