57 results about "Digital image analysis" patented technology

Methods, apparatuses, and systems for digital image analysis for device navigation in tissue are disclosed. The disclosed system uses real-time angiography and artificial intelligence to navigate an end effector of a surgical robot through a patient's vasculature to provide a surgical intervention. Digital imaging is performed that enables three-dimensional mapping of the patient's vasculature. Locations and movement of the end effector of the surgical robot are determined. The end effector is used to perform an intervention such as the removal of a blood clot or delivery of a drug for dissolving a blood clot.

The invention belongs to the technical field of image processing, and discloses a remote digital image analysis cooperation system. The virtual diagnosis module is used for collecting a continuous pathological section sequence and carrying out space registration to obtain a registration section; the model building module is used for performing three-dimensional voxel reconstruction on the registration slices to obtain a three-dimensional voxel reconstruction model, and performing semantic enhancement to obtain a three-dimensional pathological voxel model; the collaborative interaction module is used for generating virtual avatars of G experts based on the VR technology, labeling the three-dimensional pathological voxel model and obtaining space anchor point labeling data of the experts; the graph driving module is used for constructing a structured semantic tree according to the space anchor point annotation data, detecting annotation conflicts and obtaining an annotation conflict detection result; the conflict resolution module is used for performing conflict resolution on the marking conflict detection result to obtain a consensus suggestion; the collaborative efficiency and conclusion reliability of remote diagnosis are improved, and a systematic solution is provided for precise diagnosis of complex pathological cases.

The invention provides a digital image correlation strain measurement system and method based on a super-structure lens. The system comprises the super-structure lens, a digital camera, an illumination light source and a computer. The super-structure lens comprises a plurality of super-structure lens units, light scattered or emitted by an object is imaged, and the formed image is located on the plane where a photosensitive chip of the digital camera is located. The digital camera is used for acquiring an image of a measured object formed by the super-structure lens; the computer is used for processing the calibration and experiment image data acquired by the digital camera, calculating camera parameters through the calibration image, and performing three-dimensional digital image analysis and calculation on the experiment image to obtain the three-dimensional shape, displacement and deformation data of the measured object; according to the invention, 3D-DIC measurement can be realized by only adopting single shooting of one camera, and a conventional lens is replaced by the metamaterial lens, so that a simpler and more compact optical structure can be obtained on the premise of keeping the imaging quality, and the 3D-DIC measurement device has the characteristics of high efficiency, no need of camera synchronization and the like.

Method, system and computer program product for providing an output digital video stream, comprising:continuously collecting a real-time first primary digital video stream;performing a first digital image analysis of the first primary digital video stream to identify at least one first event or pattern, resulting in a first production control parameter being established at a first time delay in relation to a time of occurrence of said first event or pattern in the first primary digital video stream;applying said first production control parameter to said first primary digital video stream, resulting in the first primary digital video stream being modified without being delayed by said first time delay, so as to produce a first produced digital video stream; and continuously providing said output digital video stream based on said first produced digital video stream.

In some examples, a computerized system for analyzing images comprises at least one programmable processor and a machine-readable medium having instructions stored thereon which, when executed by the at least one programmable processor, cause the at least one programmable processor to execute operations comprising training an autoencoder using a plurality of image model training samples, the autoencoder comprising a plurality of interconnected layers and combined instances of neural networks, passing input data into a trained autoencoder model, the input data including at least one pixel image, encoding the input data into a compressed version of the input data, and decoding the compressed version of the input data to generate to create an output, the output including a sparse reconstruction of the input data, the output including a predicted pixel image label or score.

The invention relates to the technical field of image processing, and discloses a stamping part stamping forming quality detection method, which comprises the following steps: acquiring a surface digital image of a stamping part, analyzing the surface curvature and the material thickness change gradient of the stamping part, and generating a space prior weight map; calculating the structure tensor of a pixel point, and determining the orientation and axial length ratio of an elliptical sampling neighborhood; pixel point sampling is carried out along the elliptical sampling neighborhood to obtain an initial three-valued mode code; a global feature histogram is constructed, the contribution degree is accumulated to the statistical unit, and the contribution degree is the corresponding weight value of the pixel point in the spatial prior weight map; all the global feature histograms are cascaded to generate cascaded feature vectors; and inputting the cascade feature vector into a support vector machine classification model, and judging whether the stamping part to be detected is qualified or not. According to the method, the space prior weight map is introduced, the prior knowledge of the punch forming process is fused into the feature extraction process, so that the detection focuses on the defect high-incidence area, the extracted features are more targeted, and the detection accuracy is improved.

A machine learning (ML) system and methods are provided that are configured to correlate text data with corresponding image data for image sentiment analysis. The system includes a processor and a computer readable medium operably coupled thereto, the computer readable medium comprising a plurality of instructions stored in association therewith that are accessible to, and executable by, the processor, to perform image processing operations which include receiving image data for an image posted on a social networking platform, determining whether there is text data, performing image data extraction operations, analyzing the text data, determining and combining a score for the image and text data, determining an image sentiment or a text sentiment, calculating weighted metrics based on the image sentiment or the text sentiment, determining historical customer data interactions of the customer, and recommending one or more actions based on the weighted metrics.

The invention discloses a large-scale visualized direct shear test device and method for geosynthetics. The device comprises a main frame, an upper shear box, a lower shear box, a normal cyclic loading system, a horizontal cyclic shear loading system, a data acquisition system and a visualized monitoring system. The direct shear test device is characterized in that the direct shear test device can perform normal and horizontal cyclic loading at the same time, and normal stress with different frequencies and amplitudes can be applied according to needs to simulate a test of the characteristics of the reinforcement-soil interface under the cyclic loading effect; one side wall of the upper shear box and one side wall of the lower shear box are transparent observation windows, and a high-speed camera and a digital image analysis method are combined, so that the shear band evolution process can be visually observed and quantitatively analyzed; the shear box is large in size, and the size effect is effectively overcome. According to the invention, the interface characteristics under the cyclic load effect in the road engineering can be reflected more truly and comprehensively, the size and the function of the shear box are comprehensive, and the interface mechanical characteristics and the interaction mechanism under various working conditions can be simulated.

Embodiments of the present invention provide systems, methods, and computer readable media with instructions for identifying the gender of a chick. The method includes moving the chick along a path associated with a stimulus for stimulating an open gesture of the chick. The method further includes obtaining one or more images of the chick in the open posture, determining one or more gender-related features of the chick based at least in part on the one or more images, and determining a gender of the chick based at least in part on the one or more gender-related features. One or more portions of the method may include any kind of machine learning techniques, such as supervised machine learning and / or unsupervised machine learning. For example, a supervised machine learning method may be employed to train a neural network to identify a gesture of a chick, identify gender-related features associated with wings of the chick, and / or evaluate gender-related features for gender determination.

The invention relates to the technical field of de-printing and de-printing, in particular to an offset printing intermediate color intelligent generation method and system based on digital image analysis, and the method comprises the steps: obtaining to-be-de-printed order information, and obtaining a de-printed image based on the to-be-de-printed order information; obtaining deprinting color information according to the deprinting image, and generating a deprinting color allocation instruction based on the deprinting color information; in response to the deprinting color allocation instruction, deprinting color parameters are obtained, and a deprinting color matching index is obtained based on the deprinting color parameters; and obtaining deprinting color injection data according to the deprinting color matching index, and deprinting a target object based on the deprinting color injection data. The method has the effects of accurately blending the deprinting color and improving the deprinting quality.

Systems and method for providing information about a location with image analysis are described herein. The method can include: retrieving, from a user's device, location information, receiving a digital image of an location captured by a digital camera connected to the user's device, analyzing the digital image to detect an identification feature, determining an identify of the location based on the location information and the identification feature, identifying a capture time of day at which the digital image was captured, determining a median rate of traffic at the establish at the identified capture time of day, calculating information based on the median rate of traffic at the capture time of day, the information related to how crowded the location is at the captured time of day, and providing, by a display on the user's device, the information.

The invention relates to the technical field of nondestructive testing of low-carbon steel, and particularly discloses a thermal double-sensitive composite coating as well as a preparation method and application thereof. The thermal double-sensitive composite coating comprises a stress sensitive fluorescent layer and a thermochromic layer, the stress sensitive fluorescent layer adopts core-shell hybrid particles with a force-induced fluorescence enhancement effect as key functional filler, and the thermochromic layer adopts an IPN-based irreversible thermochromic material as a core functional material. The stress-sensitive fluorescent layer and the thermochromic layer are prepared from novel self-made functional materials, so that the thermal double-sensitive composite coating has the functions of high-sensitivity signal sensing, optical enhancement and permanent recording, and is assisted by a load excitation and digital image analysis process; stress-temperature coupling field information excited by the deep defect under the load is converted into a visual signal which is high in strength, high in anti-interference performance and capable of being recorded permanently, and accurate positioning, quantification and classification of the defect are achieved.

The present invention discloses a method for calculating the embedding degree of proppants based on Matlab parsing digital image technology, which includes the following processes: performing a proppant embedding experiment under a target closure pressure by using a rock column and proppants wrapped with a fluorescent agent on the surface; after the proppant embedding experiment under the target closure pressure is completed, removing the proppants on the surface of the rock column, taking a photo of the embedding surface of the rock column under dark conditions to obtain an image of the embedding surface of the rock column; preprocessing the image of the embedding surface of the rock column with Matlab to obtain a binary grayscale image; using the sum function and numel function in Matlab to calculate the area and degree of proppant embedding in the rock column in the binary grayscale image. The present invention can accurately calculate the area and degree of proppant embedding on the surface of the rock column under different formation closure pressure conditions during the hydraulic fracturing process through Matlab parsing digital image technology. Its principle is reliable, the measurement method has high precision, and it can accurately represent the proppant embedding degree during the hydraulic fracturing process.

Techniques for scanning physical media on physical items and providing information about those physical items are provided. In one technique, a digital image that is generated by a mobile device and that indicates a list of ingredients in an item is identified. Text that contains the list of ingredients is identified within the digital image. It is determined whether a particular ingredient in the list of ingredients satisfies one or more criteria. In response to determining that the particular ingredient satisfies the one or more criteria, the digital image is modified by causing a portion, of the text within the digital image, that corresponds to the particular ingredient, to be highlighted while the digital image is displayed on a screen of the mobile device. In a related technique, the mobile device performs all the steps, whereas in another technique, a remote server performs one or more of the steps.

The present invention discloses a method for identifying different types of crack extensions in laminated shale based on digital images, and relates to the field of laminated shale oil and gas exploration and development. The present invention first takes samples on site, and then performs explicit processing on sample features, uses a two-dimensional convolution model to extract lamination type features, selects laminated shale that meets the conditions, and performs speckle production on the laminated shale, and then performs mechanical experiments, and simultaneously performs digital image acquisition, uses a high-speed camera to capture synchronous images, analyzes the acquired image data and a series of experimental data obtained from mechanical test experiments, and uses a reliability-oriented initial value transfer strategy algorithm in the area of ​​interest to obtain visualized displacement data, and finally identifies the crack type. The present invention realizes the identification of laminated shale features, obtains a laminate grayscale map, selects appropriate laminated shale for digital image analysis, and obtains a digital image analysis map. Finally, the crack type is identified by calculation.

The present disclosure describes a system and method for using image processing to check color application and to indicate to a user where color application is erroneous. The system and method may include capturing a first digital image of an object before color is applied and a second digital image after color is applied. Then, the first and second digital images may undergo editing processes to prepare the digital images for analysis, analysis to determine colors in the digital images, and the generation of heatmaps in a third digital image showing errors in the application of color.

A method to execute a weld of an electrode of a cell which is part of a battery and having the steps of: causing the electrode to come into contact with another element to which the electrode must be welded; locally heating the electrode and the other element so as to locally cause a melting of the metal making up the electrode and of the metal making up the other element in order to generate a weld pool; waiting for the weld pool to cool down, thus giving stability to the weld; capturing, by means of a video camera, a series of digital images of the weld pool during the heating; analysing the digital images in order to determine a value of at least one parameter of the welding process; and changing the execution of the melting process based on the value of the parameter.

The invention provides a wound surface area automatic calculation method, device and system and a storage medium. The wound surface area automatic calculation method comprises the following steps: S1, collecting a digital image containing a scald wound surface through a camera device, shooting the image in a non-real-time manner, and uploading the image to an attached standard ruler; and S2, during real-time measurement, measuring the distance between the wound surface and the camera, calculating the radius of a picture shot by the camera device by using a trigonometric function, and further calculating the shooting area corresponding to the shot picture. And calculating the number of pixel points in a unit area according to the pixels of the shot picture. During non-real-time shooting, the number of pixels corresponding to the unit length of the standard ruler is measured, and the total area of the image is calculated according to the proportional relation between the actual size of the unit length and the number of the pixels. The wound surface area automatic calculation method, device and system and the storage medium provided by the invention have the advantages that the operation is simple and convenient, the result is objective, accurate measurement of the scald area is realized through digital image analysis, and the clinical evaluation accuracy can be remarkably improved.

The present application is directed to identifying a gender of a chick. A method includes: causing a chick to transition along a path that is associated with a stimulus for provoking an open stance by the chick; obtaining one or more images of the chick in the open stance; determining one or more gender-related features of the chick based at least in part on the one or more images; and determining a gender of the chick based in part on the one or more gender-related features. One or more portions of the method can include any various machine learning techniques, such as supervised machine learning and / or unsupervised machine learning. For example, a supervised machine learning approach can be employed to train a neural network to identify a pose of a chick, identify gender-related features associated with the chick's wing, and / or assess the gender-related features for making a gender determination.

The disclosed devices, systems and methods relate to various devices, systems and methods related to objectively analyzing digital images of turfgrass to rate various parameters and to objectively measure overall quality. The system establishes thresholds and may execute a series of steps to determine green coverage, color, density, and uniformity. The system can scale images to determine uniformity.

A system and method that identify a person at a bank branch, obtain information about the person, tailor certain bank products and services for the person based on the information about the person and present the tailored products and services to the person. The method includes taking images in the bank branch including images of bank branch customers, processing the images provided by the imaging system using a machine learning model, identifying a particular person in the images that is a customer of the bank, processing data and information about the identified person using the machine learning model, identifying bank products and services that are tailored to the identified person based on the processed data and information using the machine learning model, and providing information about the bank products and services to the bank branch in real time while the identified person is still at the bank branch.

The present invention relates to systems, methods and products for analyzing digital images, in particular digital pathology images.

The invention relates to a method for detecting structural defects of a wrapped yarn comprising a core formed of parallel fibres, whereby the core is bound together by a fibre wrapping layer comprising wrapping fibres and wild fibres, wherein an image of the moving yarn is captured by at least one optical yarn sensor over at least a part of the yarn length, whereby the optical yarn sensor comprises at least one row of radiation sensitive elements and at least one radiation source, and the optical sensor is connected to an electronic device equipped with software, whereby the captured yarn image is processed by a digital image analysis method to obtain data about the yarn surface structure, based on the obtained data, changes of the yarn surface structure along the yarn length are evaluated, these changes of the yarn surface structure are compared to preset criteria, and if these changes of the yarn surface structure exceed these preset criteria, the relevant position of the yarn is determined as the occurrence of a yarn structural defect. Furthermore, the invention relates to an apparatus, a computer program and a computer readable medium for carrying out the method.

This invention proposes a feature extraction method for texture images, belonging to the field of digital image analysis and image classification technology. The feature extraction method includes: inputting the texture image into a feature extractor based on the Vision Mamba architecture to extract a high-level feature map of the texture image; performing spatial domain processing and frequency domain processing on the high-level feature map in parallel to obtain a spatial feature map and a frequency feature map, respectively; and fusing the spatial feature map and the frequency feature map through a bidirectional cross-attention mechanism to generate a fused feature map. The feature representation generated by this method integrates spatial details and frequency structure information, exhibiting stronger discriminative power and robustness to disturbances such as scale and deformation. Furthermore, leveraging the efficient computational characteristics of its backbone network, it can quickly complete feature extraction with lower resource overhead, thereby providing higher-quality and more efficient feature input for downstream recognition tasks.

Embodiments of the present disclosure provide a system, method, and computer-readable medium with instructions for identifying the gender of a chick. The method includes moving the chick along a path associated with a stimulus means for inducing an open posture by the chick. The method further includes acquiring one or more images of the chick in an open posture, identifying one or more gender-associated features of the chick based at least in part on the one or more images, and determining the gender of the chick based at least in part on the one or more gender-associated features. One or more portions of the method may include any of a variety of machine learning techniques, such as supervised machine learning and / or unsupervised machine learning. For example, a supervised machine learning approach may be used to train a neural network to identify the pose of the chick, identify gender-associated features related to the chick's wings, and / or evaluate the gender-associated features to make a gender determination.

This invention belongs to the field of image processing technology and discloses a remote digital image analysis collaborative system. It includes: a virtual diagnosis module: acquiring continuous pathological slide sequences and performing spatial registration to obtain registered slides; a model building module: performing three-dimensional voxel reconstruction on the registered slides to obtain a three-dimensional voxel reconstruction model, followed by semantic enhancement to obtain a three-dimensional pathological voxel model; a collaborative interaction module: generating G virtual avatars of experts based on VR technology, annotating the three-dimensional pathological voxel model, and obtaining spatial anchor point annotation data for the experts; a graph-driven module: constructing a structured semantic tree based on the spatial anchor point annotation data, detecting annotation conflicts, and obtaining annotation conflict detection results; and a conflict resolution module: resolving conflicts in the annotation conflict detection results to obtain consensus suggestions. This invention improves the collaborative efficiency and reliability of conclusions in remote diagnosis, providing a systematic solution for the accurate diagnosis of complex pathological cases.

The invention belongs to the technical field of pipeline robots, and particularly relates to a control method and device suitable for a seawater pipeline coating removing robot, and the control method comprises the steps: 1, obtaining the walking data of the robot in a pipeline, and controlling the walking route of the robot; 2, a high-pressure water gun is adopted for spraying the seawater pipeline to remove a coating, a pipeline inner wall image sprayed by the robot is captured and captured in real time, and the sprayed pipeline inner wall image is obtained; 3, performing digital image processing on the sprayed pipeline inner wall image to obtain a digital image analysis result; 4, the cleaning effect of the robot is judged according to the digital image analysis result; 5, according to the cleaning effect of the robot, whether the moving speed of the robot and the cleaning frequency of the high-pressure water gun are adjusted or not is judged. The visual module with a visual detection function is adopted, the inner wall of the cleaned pipeline can be captured in time, images are processed, and the moving speed and the cleaning frequency of the robot are adjusted according to the processing result.

Techniques for scanning physical media on physical items and providing information about those physical items are provided. In one technique, a digital image that is generated by a mobile device and that indicates a list of ingredients in an item is identified. Text that contains the list of ingredients is identified within the digital image. It is determined whether a particular ingredient in the list of ingredients satisfies one or more criteria. In response to determining that the particular ingredient satisfies the one or more criteria, the digital image is modified by causing a portion, of the text within the digital image, that corresponds to the particular ingredient, to be highlighted while the digital image is displayed on a screen of the mobile device. In a related technique, the mobile device performs all the steps, whereas in another technique, a remote server performs one or more of the steps.

The application provides a coarse-grained aggregate mechanical behavior continuous-discontinuous numerical calculation method, including: establishing a numerical model of coarse-grained aggregate, the numerical model including a constant strain elastic triangular element and an initial thicknessless cohesive force element distributed along the boundary of the triangular element; determining the constitutive relation of the cohesive force element in the numerical model under a continuous deformation analysis framework; determining the contact relation between discrete triangular elements in the numerical model under a discontinuous deformation analysis framework; obtaining a continuous-discontinuous coupling model of the coarse-grained aggregate based on the determined constitutive relation and contact relation, inputting boundary constraint conditions and external loads into the continuous-discontinuous coupling model according to actual working conditions, and performing simulation calculation to obtain the mechanical properties and deformation failure forms of the coarse-grained aggregate under external loads. The application establishes a corresponding numerical model through digital image analysis and recognition technology, completes continuous-discontinuous coupling calculation of the mechanical behavior of coarse-grained aggregate, and takes into account solving accuracy and calculation efficiency.

This invention discloses a multi-gene mutation prediction method based on a combination of multi-task and multi-instance learning. Belonging to the fields of digital image analysis, pathology, and machine learning, the specific steps are as follows: Preprocessing existing pathological image data by staining normalization; constructing a feature matrix for each pathological image, and further using a two-layer multi-instance learning method to construct a package for each pathological image; constructing a multi-task deep learning network based on transformer and MobileNet; applying the model to a test set and outputting pathological image analysis results. This invention employs a multi-task deep neural network and applies it to the task of predicting multiple gene mutations based on pathological images. Compared to traditional single-task networks, this invention can simultaneously predict the results of multiple tasks, saving computational resources while improving accuracy; furthermore, combining the transformer module with traditional convolution considers both local and global features.