709 results about "Product image" patented technology

The present invention relates to a system (100) and method (300) for automated product validation, identification, and transaction management in shopping environments. The system (100) integrates a smart shopping cart (102) equipped with at least one camera (106), a load cell (108), and a user interface (110). An AI model trained on a dataset of high-resolution, 360° product images generate unique image embeddings for each product. The system performs multimodal validation by comparing the extracted image embeddings, measured weight data, and scanned barcode information with reference data stored in a vector database. Further, discrepancies, such as unscanned products or mismatches, are flagged, and payment is blocked until resolved.

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 the technical field of industrial detection, and discloses a multi-modal data fusion industrial defect intelligent detection system, which comprises a multi-modal data acquisition module which comprises a high-resolution visible light camera, an infrared thermal imager and an ultrasonic sensor and is used for acquiring product images and data information from different dimensions, the devices are reasonably arranged on a production line to realize comprehensive acquisition; the preprocessing module is used for denoising and normalizing the collected data; the limitation of single-mode detection is overcome through the multi-mode data acquisition module, and omnibearing detection is realized; an advanced fusion strategy is adopted, and feature interference and insufficient information interaction are avoided; the environment self-adaptive adjustment module enables the system to stably work in a complex environment; the parallel computing module improves the data processing efficiency and meets the real-time detection requirement; the encryption module ensures data security, the modular design facilitates maintenance and upgrading, and the data backup and recovery module ensures production and data integrity.

The invention discloses a concave-convex point detection and defect evaluation system based on multistage detection and feature change, and the system comprises an image collection unit which is used for capturing a product image in real time; the image preprocessing unit is used for carrying out noise reduction processing on the image and improving the brightness and the contrast ratio of the image; the primary product defect positioning module is used for selecting Gaussian difference extraction, dynamic threshold extraction, fixed threshold extraction, template matching and a deep learning algorithm module to extract and position suspicious defects according to the size of the product and the characteristic form of the defects; the secondary defect classification and judgment module is used for carrying out preliminary classification and type judgment on the defects in the region; the third-stage defect contour extraction unit is used for performing fine contour extraction on each detected defect area after the defect classification is clear; and the four-stage defect feature analysis and evaluation unit is used for deeply extracting key features of each defect and carrying out scientific and quantitative evaluation on the key features.

The invention discloses a rendering-based artificial industrial product defect synthesis method and device. Firstly, modeling and generalization are carried out on the reasonable shape of a 3D model of a normal sample; the modeling defect result of the target sample is simulated by modifying the shielding, the metallization and the roughness, the three variables are designed into parameters or variables which can be updated, and defect simulation is carried out on the corresponding area according to a subsequent loss function. And projecting the sample 3D model into which the defect is introduced into a standard space to obtain an industrial product image of the multi-view defect product with the standard resolution. Calculating image similarities of different artificial samples and a small number of real defect samples; label-based discrimination is carried out on a real sample and a defect sample through an adversarial network of an image, and the similarity between a generated defect and an actual defect is improved through loss functions of the two parts. According to the method, a multi-view defect generation result is optimized instead of evaluating and simulating defects in pixel.

Methods, systems, and computer-readable storage media for receiving a product image depicting a product that is to-be-inspected for defects, transmitting a request to a LLM system, the request including the product image and a reference image, receiving, from the LLM system, a textual response, the textual response being generated by the LLM system at least partially by processing the product image and the reference image, processing the textual response and the product image through a RIS model to provide an output image that includes one or more masks, each mask indicating a defect in a product depicted in the product image, and providing the output image with an indication that the product is defective.

An online system performs an inference task in conjunction with the model serving system and / or interface system to generate relevant product images for query auto-completion and query suggestion to help users better navigate their search experience. The online system generates a collection of query suggestions using search query log mining. For each query suggestion in the collection of query suggestions, the online system retrieves one or more catalog images that depict the query suggestion from a product catalog. The online system constructs a prompt to a text-to-image model including the query suggestion, and a request to generate one or more query images based on the query suggestion. The online system receives the query images from the text-to-image model and ranks the catalog and query images to identify an image to display to the user in association with the query suggestion.

The invention relates to the technical field of big data analysis, and more particularly discloses a package design optimization system and method based on big data analysis, which analyze and optimize package design by using a product image and a package design image. The attractive force and the spreading effect of product packaging are improved in the modes of color adjustment, pattern optimization, information transmission improvement and the like, so that the high requirement of consumers for visual experience is met, and a packaging design scheme with better attractive force and information transmission effect is provided for the fields of beauty makeup commodities and the like.

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 belongs to the technical field of printing process optimization, and discloses a printing process optimization decision-making system based on big data. Comprising an image acquisition module used for acquiring a printed product image; the feature extraction module is used for analyzing the printed product image and extracting product feature data; the quality detection module is used for analyzing the product feature data and identifying quality defect problems; the reason tracing module traces the reason of the quality defect according to the quality defect problem; the process optimization module is used for dynamically optimizing printing process parameters based on quality defect reasons; according to the method, the advantages of advanced technologies such as computer vision, machine learning and intelligent optimization can be fully played, intelligent monitoring and dynamic optimization of the whole printing production process are achieved, the method can rapidly adapt to the changing production environment, the quality defect problem in printed products is reduced, and the printing quality and the production efficiency are improved.

The invention discloses a zero-sample industrial defect detection method and device based on visual enhancement and a medium, and the method comprises the steps: collecting an industrial product image and a text semantic tag corresponding to the industrial product image, and constructing a training set and a test set; building a zero-sample industrial defect detection model based on visual enhancement, and training by using the training set; and inputting the test set into the trained model for reasoning and evaluation. The model is composed of a text encoder and an image encoder, and deep interaction and optimization of text and image features are realized by introducing a bidirectional cross attention mechanism, a multi-task fusion module and an image feature refining module. In the training stage, the model learns uniform defect features from part of industrial product categories; in the test stage, defect identification and positioning are carried out on the types of industrial products which are not contacted. According to the method, the dependence on manual labeling is effectively reduced, the adaptability and detection precision of the model in a complex industrial scene are improved, and the method has good generalizability and industrial deployment value.

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 discloses an e-commerce commodity image-text generation optimization system based on generative AI, relates to the technical field of image-text optimization, and is used for solving the problems of insufficient image-text attraction and low conversion rate caused by difficulty in generating differentiated image-text content for different user groups. Classifying and marking the commodities, judging attention conditions, extracting commodity core features and user preference features after screening, and determining a user interest weight value of each marked commodity; feedback information of the commodities under the corresponding classification marks is collected, image-text information is generated in combination with user interest weights, updating time is set to collect historical optimization effect data, and the historical optimization effect data is used for updating user behavior data, so that image-text optimization of different commodities is achieved, and the matching degree and the display attraction of contents and user preferences are improved.

The present invention discloses a method and system for industrial defect detection and localization based on frequency domain enhancement, which relates to the fields of computer vision and image processing, can discover abnormal patterns in industrial images from multiple perspectives, and also has a relatively fast inference speed. The method includes: processing an input image through a high-pass filter to obtain a high-frequency image; inputting the original image and the high-frequency image into an improved U-Net network integrated with a dual-domain feature selection module; performing image reconstruction simultaneously in the spatial domain and the frequency domain; calculating an anomaly score and a localization map based on the reconstruction results. By combining spatial domain and frequency domain analysis, the present invention realizes a comprehensive characterization of local pixel changes and global frequency patterns in the image, improving the accuracy of anomaly detection and localization. The method has achieved optimal performance on multiple real industrial scenario datasets. The present invention is applicable to anomaly detection and anomaly area localization of industrial product images.

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.

The invention is suitable for the technical field of virtual fitting, and particularly relates to an e-commerce virtual fitting method and system based on multi-modal query, and the system comprises a graph-graph module which is used for starting from a blurred image / video and matching to a real commodity graph; the text-graph module is used for matching a real commodity graph starting from the query text; the virtual fitting module is used for generating a freely editable portrait with fixed clothes and optional conditions; and according to query modal information input by a user, automatically selecting a corresponding query module, and inputting the matched commodity clothing image into a virtual fitting module to generate a virtual fitting image. According to the method, large model assistance and a potential diffusion model are introduced, and a multifunctional plug-in is combined, so that one-stop operation is realized, free and editable virtual fitting images are completed, the shopping experience of a user can be remarkably improved, refunding and changing caused by improper goods are reduced, the operation cost of a merchant is reduced, and meanwhile, comprehensive and personalized clothing display of the merchant is supported.

The invention relates to the technical field of quality evaluation, and particularly discloses a rubber and plastic sealing element quality evaluation method and system based on big data analysis, and the method comprises the steps: training a normal appearance model based on an unsupervised model architecture through constructing and dynamically managing a dynamic baseline library only containing good rubber and plastic sealing element images; learning the internal characteristic mode of the image of the good rubber and plastic sealing element; furthermore, in a quality evaluation stage, a to-be-detected rubber and plastic sealing element image is input into the trained normal appearance model, the normal appearance model carries out image reconstruction on the to-be-detected rubber and plastic sealing element image based on a good product image internal characteristic mode learned by the normal appearance model, and an image reconstruction error is calculated to serve as an abnormal score of the detected image. Therefore, the defect evaluation of the rubber and plastic sealing element is realized. The method not only improves the detection precision and efficiency, but also reduces the collection and labeling cost of the training data, and can meet the detection requirements of novel or accidental defects at the same time.

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 relates to the technical field of computer vision, in particular to a product design optimization system and method based on an image model. The method comprises the following steps: obtaining a product image, and carrying out image preprocessing to obtain a to-be-processed product image; performing image enhancement processing based on the to-be-processed product image to obtain a product enhancement image; constructing an image model based on the product enhanced image; detecting product surface scratches based on the product enhanced image to obtain product scratch data; marking a seriously scratched area according to the product scratch data; evaluating the anti-corrosion capability of the coating based on the seriously scratched area; a product anti-corrosion layer covering structure is optimized according to the anti-corrosion capacity of the coating; detecting product stains according to the severely scratched area to obtain product stain data; and speculating the product pollution process flow based on the product stain data. According to the invention, integration of defect identification and process optimization driven by a product image is realized based on a computer vision technology, and the precision and response efficiency of product design optimization are improved.

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 embodiment of the invention provides an industrial product anomaly detection method and a related device. The method comprises the following steps: acquiring an industrial product image; performing image mask processing on the industrial product image to generate a mask feature image; inputting the mask feature image into a feature extraction module to determine an abnormal region in the industrial product image, continuously optimizing and balancing the attention weight of a feature part according to an abnormal score obtained by calculation, and inputting an obtained model parameter into an adaptive moment estimation optimization module for gradient optimization to obtain an abnormal soft label data set; inputting the abnormal soft label data set into a student model, and adjusting parameters through back propagation to obtain a detection result of the student model; and a detection result is transmitted to a terminal in a data visualization mode, and the terminal sends a rejection instruction to control a mechanical arm to automatically reject abnormal products. Based on this, the embodiment of the invention has an unsupervised learning capability and a few-sample detection capability, and can well meet the requirements of industrial enterprises for various anomaly detection.

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 present disclosure relates to a computer-implemented method for generating an advertisement image, an apparatus for generating an advertisement image, and a computer-readable non-transitory storage medium storing a program. According to one embodiment, the computer-implemented method for generating an advertisement image includes: generating textual control parameters for an AI image generation model based on a textual description of an advertisement image of a product; generating an image space control parameter for an AI image generation model based on a product image whose foreground is an image block indicating a product and whose background is a single color; generating a noise image for an AI image generation model based on the product image; generating an initial product image based on the text control parameter, the image space control parameter and the noise image by using an AI image generation model; generating a restored product image by replacing corresponding regions in the initial product image with the image blocks; and generating an advertisement image of the product by performing post-processing of fusing the foreground image and the background image on the restored product image.

The invention discloses an industrial product defect detection system and method based on multi-granularity auto-encoders, and belongs to the field of product detection.The system comprises a service layer and a display layer, and the service layer comprises a reconstruction module, a decoding module and a display module, performing data reconstruction of space granularity, feature granularity and color granularity on an input product image to obtain a reconstruction error matrix of each granularity; the fusion module fuses the reconstruction error matrix of each granularity to obtain a comprehensive reconstruction error graph; the defect detection and positioning module is used for performing threshold segmentation on the comprehensive reconstruction error image, preliminarily calibrating pixels exceeding a set threshold as defect areas, and performing accurate acquisition of defect boundaries on the preliminarily calibrated defect areas by using a positioning algorithm; and the display layer maps the defect area into an abnormal thermodynamic diagram, and the abnormal thermodynamic diagram is displayed after being superposed with an original input image. According to the method, complex defect features can be extracted, feature expression quality is improved, and defects are accurately positioned and displayed.

The invention discloses a data processing method and system based on an electronic component product data dictionary. The data processing method comprises the following steps: obtaining product data of an electronic component product to be processed; and calling a preset electronic component data dictionary tool. And inputting the basic information of the product into the electronic component data dictionary tool for matching, and obtaining a plurality of first matching results which are output by the electronic component data dictionary tool and are matched with the basic information of the product. And matching the parameter information with the standard data of the plurality of first matching results, and outputting a plurality of second matching results matched with the parameter information. And matching the product picture with the standard data of the plurality of second matching results, and outputting a final matching result matched with the product picture. And replacing the product data of the electronic component product with the standard data of the standard electronic component corresponding to the final matching result.

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.