Abstract: There is provided a technique that includes: a camera configured to capture images of the target object; a memory configured to store the images of the target object and feature data including one or more predetermined exterior features of the target object; and a processor configured to: determine a first process configuration for an operation including a plurality of image processes; perform the operation under the first process configuration; generate inspection data from the sets of images that have been processed; generate an inspection score by comparing the inspection data with the feature data; compare the inspection score with a predetermined threshold score; set the first process configuration as an optimal configuration if the inspection score satisfies the predetermined threshold score.

Abstract: A system, apparatus, computer program product, and a method for manufacturing an unconsolidated composite material. Sensor data is received from a sensor system for a composite material manufacturing system. The sensor data is received during manufacturing an unconsolidated composite material by the composite material manufacturing system. A set of predicted properties is determined for a number of portions of the unconsolidated composite material using the sensor data. The set of predicted properties is for the number of portions of the unconsolidated composite material as a completed product. A corrective action is performed based on a quality level for the number of portions of the unconsolidated composite material.

Abstract: A machine-vision system for monitoring a quality metric for a product. The system includes a controller configured to receive a digital image from an image acquisition device. The controller is also configured to analyze the digital image using a first machine-vision algorithm to compute a measurement of the product. The system also includes a vision server connected to the controller, and configured to compute a quality metric and store the digital image and the measurement in a database storage. The system also includes a remote terminal connected to the vision server, and configured to display the digital image and the quality metric on the remote terminal.

Abstract: A marking system for decorating one or more workpieces includes a plurality of marking stations that can mark product images on blank workpieces to produce product workpieces, at least some of which have different sizes, shapes, materials, or a combination thereof, a control system that can select one of the plurality of marking stations and send product image data to the selected one of the plurality of marking stations, and a robotic manipulator that can transport a blank workpiece to the selected marking station under the control of the robotic manipulator. The selected marking station can mark the product image the blank workpiece based on the product image data which produces a product workpiece. The robotic manipulator can remove the product workpiece from the selected one of the plurality of marking stations.

Abstract: A workpiece inspection device 1 includes a table (3), image capturing unit fixing part (7), first light projection unit (4), second light projection unit (5), linear movement mechanism (8), turning mechanism (9), quality determination unit (10), and control unit (11). The control unit (11) performs first image capturing step of causing first light projection unit (4) to project light and causing image capturing unit (6) to capture image, detailed inspection portion-determination step of setting, portion of workpiece (2) determined to require detailed inspection based on image captured in the first image capturing step, second image capturing step of causing second light projection unit (5) to project light onto the workpiece (2) and causing image capturing unit (6) to capture image of the detailed inspection-requiring portion, and quality determination step of determining quality of the detailed inspection-requiring portion based on image captured in the second image capturing step.

Abstract: A laser irradiation apparatus includes a stage on which a substrate is provided, a laser irradiation unit which irradiates a laser to the substrate on the stage, an image acquiring unit which acquires an image of a predetermined region of the substrate, and a control unit electrically connected to the laser irradiation unit and the image acquiring unit, where the control unit calculates a brightness value corresponding to an average value of grayscale values of the image provided from the image acquiring unit, compares a calculated brightness value with a reference brightness value, and outputs data on performance of the laser based on a result of comparing the calculated brightness value with the reference brightness value.

Abstract: A LIDAR device is positioned on a crane and is moved along a track to collect 3D image data of the area below the crane. The resulting image data is sent to a computing device that applies or more filtering algorithms to the image data and searches for known image shapes therein through a comparison of the image data and one or more 3D object models based on known shapes or geometric primitives. If an object is identified in the image data and is determined to be accessible, position information for that object may be sent to a device configured to control movement of the crane to grab/pick up the object.

Abstract: This disclosure provides systems, methods, and apparatus detecting defects in a substrate. An image of the substrate is compared with a reference image to identify potential defects. Images corresponding to the potential defects are processed sequentially by a set of classifiers to generate a set of images that include a defect. The set of classifiers can be arranged to have increasing accuracy. A subset of the images corresponding to the potential defects is processed by a type classifier that can determine the type, size, and location of the defect in the images. The defects can be further processed to determine the severity of the defects based on the location of the defects on the substrate.

Abstract: In order to improve a user's task of documenting items that are identified by the user while at a construction site, a computing system may be configured to (i) analyze media content captured at a construction site (e.g., an audio or audiovisual recording) that is descriptive of at least one given on-site item identified by a user while at the construction site, (ii) extract, from the captured media content, a set of information for the given on-site item, (iii) based on the extracted set of information for the given on-site item, generate a data record for the given on-site item, and (iv) cause the generated data record for the given on-site item to be presented to the user for review.

Abstract: A marking region image is obtained by cutting out the part corresponding to a marking region from an article image obtained by imaging an article to be inspected. Then, whether or not the marking is properly provided is determined by performing a character recognition of a marking part for a marking region image. Further, an image of an article having no marking and no defect is stored as a reference image, whereas a marking periphery image obtained by removing the image of the marking part from the marking region image is compared to the reference image. By that comparison, whether or not any defect is included in the marking peripheral part of the marking region except the marking part is determined.

Abstract: A video recording system and method for labeling networked meetings and video/audio clips from a main stream of video/audio is disclosed and claimed. The video recording system allows a system user to selectively view and label a main video stream or video clips. A rewind control rewinds the main stream of video, and then label the selected video clip from a start pointer to an end pointer. The video recording system also allows network members to teleconference while recording a main stream of video. Any of network members can label selected sections of the teleconference in real time. Further, a recording alert control automatically displays a reminder message to a camera operator after a non-recording duration, such as 5 to 10 seconds, after the software application is opened. This feature is useful when camera operator forgets to record. A voice control feature enables voice command activation of the controls.

Abstract: A method for determining part wear, such as using a wear metric, includes receiving, from a sensor, sensor data representing a surface of a wear part. The method further includes determining distances between measured points in the sensor data and points on one or more part models, which part models may include new part models and/or worn or wear limit part models. The method further includes using a bounding model that at least partially envelopes the part model(s) and the measured points to determine a direction along which the distances are measured. The method may also include quantifying wear using the measured distances.

Abstract: A method including generating a 3-D model of an unstenosed geometry of a blood vessel responsive to a 3-D model of an actual geometry of the blood vessel, establishing a parametric description of a stent that is expanded from a collapsed configuration to a final configuration that apposes the unstenosed geometry, developing a design for the stent by varying parameters of the parametric description responsive to a design heuristic that includes risk of stent strut breakage during a plastic deformation between the collapsed configuration and the final configuration, embodying the stent according to the design for the stent, inserting the stent into a blood vessel in its collapsed configuration, maneuvering the stent through the blood vessel to a stenosis, and expanding the stent to its final configuration.

Abstract: The present invention relates to a position specifying method for specifying a position through touch input in a screen displayed on a touch panel display.

Abstract: One embodiment can provide a system for detecting occlusion at an orifice of a three-dimensional (3D) printer nozzle while the printer nozzle is jetting liquid droplets. During operation, the system uses one or more cameras to capture an image of the orifice of the printer nozzle while the 3D printer nozzle is jetting liquid droplets. The system performs an image-analysis operation on the captured image to identify occluded regions within the orifice of the 3D printer nozzle, compute an occlusion fraction based on the determined occluded regions, and generate an output based on the computed occlusion fraction, thereby facilitating effective maintenance of the 3D printer.

Abstract: There are provided methods and systems for assessing the health of an asset. For example, a system is provided. The system may include a processor and a memory including instructions that, when executed by the processor, cause the processor to perform operations consistent with identifying a defect in a component of an asset. The operations may include fetching from an inspection system, a plurality of images acquired from an inspection of the component of the asset by the inspection system. The operations may include identifying, based on an image processing technique codified and included as part of the instructions, a subset of images from the plurality of images. The subset of images is representative of the defect in the component of the asset, and the image processing technique is selected from the group consisting of an auto-distress ranking technique, a structural similarity technique, a mean-subtracted filtering technique, and a Hessian norm computation technique.

Abstract: There is provided a system and method of inspecting a specimen. The method includes obtaining a first image of an inspection area of a die of a semiconductor specimen and a group of reference images corresponding to a group of candidate reference units, obtaining a second image informative of one or more partitions of the inspection area respectively associated with one or more inspection algorithms, for each given pixel of the first image, determining location of one or more reference pixels thereof based on information of the second image, selecting, from the group of candidate reference units, one or more specific reference units actually required for inspecting the inspection area based on the determined location, and using one or more reference images corresponding to the selected reference units to inspect the first image, thereby providing an inspection result of the inspection area.

Abstract: An image inspection device inspects an inspection image obtained by reading a sheet. The image inspection device includes a hardware processor that: performs inspection by comparing the inspection image with a reference image that is obtained by reading the original image that is printed on the sheet; determines whether a possibility of abnormality exists in the reference image based on a difference between the reference image and the inspection image; displays a difference portion between the reference image and the inspection image when determining that the possibility of abnormality exists in the reference image; receives a selection of a normality or an abnormality for each of the reference image and the inspection image; and replaces the reference image with the inspection image when the abnormality is selected for the reference image and the normality is selected for the inspection image.

Abstract: In one embodiment, an X-ray inspection system may access a first set of X-ray images of one or more first samples that are labeled as being non-conforming. The system may adjust a classification algorithm based on the first set of X-ray images. The classification algorithm may classify samples into conforming or non-conforming categories based on an analysis of corresponding X-ray images. The system may analyze a second set of X-ray images of a number of second samples using the adjusted classification algorithm. The second samples may be previously inspected samples that have been classified as conforming by the classification algorithm during a previous analysis before the classification algorithm is adjusted. The system may identify one or more of the second samples from the second set of X-ray images. Each identified second sample may be classified as non-conforming by the adjusted classification algorithm.

Abstract: A method and verification system for verifying pharmaceuticals packaged within a pouch using a pharmacy packaging system. The method includes activating a first light source to illuminate the pharmaceutical pouch, capturing a first image of the pharmaceutical pouch while illuminated by the first light source, activating a second light source to illuminate the pharmaceutical pouch, and capturing a second image of the pharmaceutical pouch while illuminated by the second light source. The method further includes generating a third image based on the first image and the second image, generating a dashboard to simultaneously display first images, second images, and third images from a plurality of pharmaceutical pouches, providing a number of pills indication of a number of pills detected in the pouch against a number of pills expected in the pouch, and displaying the dashboard.

Abstract: A cuvette with at least one side having materials with thermal conductivity of at least 5 W/m-K, such as sapphire, for holding contact lenses or intra-ocular lenses during optical measurements. The cuvette may further include a backstop to ensure consistent measurements and a pedestal to minimize optical measurement variations.

Abstract: Methods and systems for performing diagnostic functions for a deep learning model are provided. One system includes one or more components executed by one or more computer subsystems. The one or more components include a deep learning model configured for determining information from an image generated for a specimen by an imaging tool. The one or more components also include a diagnostic component configured for determining one or more causal portions of the image that resulted in the information being determined and for performing one or more functions based on the determined one or more causal portions of the image.

Abstract: Systems, methods and computer-readable media are provided for identifying organisms for production. The identification is based upon determining one or more outlier detection parameters for identifying outliers (e.g., outlier wells, strains, plates holding organisms) from a data set of organism performance metrics. A prediction engine may identify one or more candidate outliers based upon a first set of outlier detection parameters (e.g., outlier detection threshold), and determine probability metrics that represent likelihoods that candidate outliers belong to an outlier class. Based on those metrics, some of the outliers may be excluded from consideration in predicting organism performance for the purpose of selecting organisms for production.

Abstract: A system and method for detecting, based on a simulation of a build of an object using additive manufacturing, if the build of the object would be flawed or would fail during actual additive manufacturing of the object is provided.

Abstract: A gas detection device includes: a processor that visualizes a gas by performing image processing on infrared image data in an inspection region imaged by an imaging device; a display that displays an inspection image that reflects a result of the image processing; and an input interface that receives an input of supplementary information on the inspection image displayed on the display.

Abstract: A three-dimensional shape data editing device including a processor configured to, with regard to an object represented by a first three-dimensional shape configured using multiple forming surfaces of at least one of flat surfaces and curved surfaces, a second three-dimensional shape in which the object is configured using multiple three-dimensional elements, and a third three-dimensional shape that is converted from the second three-dimensional shape such that the object is represented by the multiple forming surfaces, specify edge forming surfaces that correspond to edges of the object extracted from the first three-dimensional shape, with respect to the third three-dimensional shape, and configure the edge forming surfaces in the third three-dimensional shape such that shapes of the edges of the object represented by the first three-dimensional shape are reproduced.

Abstract: This invention provides a system and method for finding patterns in images that incorporates neural net classifiers. A pattern finding tool is coupled with a classifier that can be run before or after the tool to have labeled pattern results with sub-pixel accuracy. In the case of a pattern finding tool that can detect multiple templates, its performance is improved when a neural net classifier informs the pattern finding tool to work only on a subset of the originally trained templates. Similarly, in the case of a pattern finding tool that initially detects a pattern, a neural network classifier can then determine whether it has found the correct pattern. The neural network can also reconstruct/clean-up an imaged shape, and/or to eliminate pixels less relevant to the shape of interest, therefore reducing the search time, as well significantly increasing the chance of lock on the correct shapes.

Abstract: An inspection apparatus including: a display device; and one or a plurality of processors, wherein the one or the plurality of processors is programmed to execute a method including: converting an inspection target image representing an inspection target into a virtual good article image by using a learning model, the learning model being trained so that an image representing a good article is generated based on features of a plurality of targets that are determined as good articles, generating a difference between the virtual good article image and the inspection target image as a defect candidate image, and displaying the defect candidate image on the display device.

Abstract: A method for analyzing 2D material thin film and a system for analyzing 2D material thin film are disclosed. The detection method includes the following steps: capturing sample images of 2D material thin films; measuring the 2D material thin films by a Raman spectrometer; performing a visible light hyperspectral algorithm on the sample images by a processor to generate a plurality of visible light hyperspectral images; performing a training and validation procedure, performing an image feature algorithm on the visible light hyperspectral images, and establishing a thin film prediction model based on a validation; and capturing a thin-film image to be measured by the optical microscope, performing the visible light hyperspectral algorithm, and then generating a distribution result of the thin-film image to be measured according to an analysis of the thin film prediction model.

Abstract: Large scale instance recognition is provided that can take advantage of channel-wise pooling. A received query image is processed to extract a set of features that can be used to generate a set of region proposals. The proposed regions of image data are processed using a trained classifier to classify the regions as object or non-object regions. Extracted features for the object regions are processed using feature correlation against extracted features for a set of object images, each representing a classified object. Matching tensors generated from the comparison are processed using a spatial verification network to determine match scores for the various object images with respect to a specific object region. The match scores are used to determine which objects, or types of objects, are represented in the query image. Information or content associated with the matching objects can be provided as part of a response.

Abstract: A tire conveying apparatus includes a conveyor for conveying a tire, a position sensor, and a controller for controlling the conveyor. The controller includes a determination unit which determines whether or not the tire is positioned within an allowable area for a reference area set in a conveyance path of the conveyor, based on a detection result of the position sensor, and a center conveyor control unit which drives the conveyor such that the tire is positioned within the allowable area, if a determination that the tire is not positioned within the allowable area is made.

Abstract: The calibrating system 100 includes a conveyance system 102 for carrying work products 104 arranged in multiple lanes extending along the conveyor to be trimmed and/or cut into portions P. A scanner 110 scans the work product and a cutter system 120 consisting of one or more cutters are arranged in an array or series of cutter assemblies for cutting the work products into end pieces P of desired sizes or other physical parameters. A processor/computer 150, using a scanning program or portioning program, determines how the work product may be portioned into one or more end piece product sets. The processor/computer using the portioning software then functions as a controller to control the cutter system 120 to portion the workpiece 104 according to the selected end product/pieces P.

Abstract: A method for manufacturing control of machining of workpieces in a manufacturing hall that includes providing a plurality of image acquisition devices configured to acquire image sequences of allocated observation areas, identifying an object to be tracked in a first image of a first image sequence using at least one object feature, determining positions of the object feature in images of subsequent image sequences, determining a current position of the object by localizing the object feature in a temporally current image of one of the image sequences, and assigning the position of the object feature in the temporally current image to a current position in the observation area of the image sequence that includes the temporally current image, and integrating the determined current position of the object into the manufacturing control of the hall.

Abstract: A method for inspecting a part in a manufacturing environment, the method including: acquiring at least one image of the part; optionally enhancing the at least one image; automatically analyzing the enhanced image to determine if the part has a potential defect; if it is determined that there is a potential defect: displaying the at least one image to an operator; and receiving operator input of a part status, wherein the part status may be defect or no defect; and storing the part status in association with the at least one image. The automatic analysis may include a confidence level and only images having a confidence level that does not meet a threshold will be displayed to an operator.

Abstract: Systems and methods for determining a customized cosmetic formulation. In one method, a user is guided to capture an image of a skin region with known lighting and color characteristics, and the image is processed to provide calibrated skin color information. A customized cosmetic formulation is automatically determined for the user based on the calibrated skin color information. In another method, a user is interactively guided through capture of one or more skin region images using a device having an image sensor. The skin region images are processed to provide calibrated skin color information, which is compared to a ground truth data set to identify a set of closest known values in the ground truth data set. A customized cosmetic formulation is automatically determined for the user based on the comparison.

Abstract: Method and system are disclosed for characterizing and quantifying composite laminate structures. The method and system take a composite laminate of unknown ply stack composition and sequence and determine various information about the individual plies, such as ply stack, orientation, microstructure, and type. The method and system can distinguish between weave types that may exhibit similar planar stiffness behaviors, but would produce different failure mechanisms. Individual ply information may then be used to derive the laminate bulk properties from externally provided constitutive properties of the fiber and matrix, including extensional stiffness, bending-extension coupling stiffness, bending stiffness, and the like. The laminate bulk properties may then be used to generate a probabilistic failure envelope for the composite laminate.

Abstract: An ingredient data system that ingests text and graphics of product labels associated with consumer products to check compliance with rules pertaining to what can be included on the product labels generally includes a memory having instructions stored thereon, and at least one processor to execute the instructions to transmit via a network a representation of a label view to a user interface on a client computing device that displays one or more of the base attributes associated with the first request, at least a portion of each of the images of one or more of the product labels of the consumer products designated under one or more of the base attributes associated with the first request, and at least a portion of details of noncompliance when one or more of the pieces of the constituent information are identified as impermissible according to the compliance information.

Abstract: Robotic inspection device for tank and pipe inspections includes a housing configured to be positioned on a portion within a flow apparatus. The portion has a wall with a coating on the wall. The coating has a coating thickness. The device has a magnetic transducer mounted to the housing. The magnetic transducer is configured to measure a magnetic flux permeability through the coating on the wall. A computer system is mounted to the housing. The computer system is operatively coupled to the magnetic transducer. The computer system includes one or more processors and a computer-readable medium storing instructions executable by the one or more processors to perform operations. The operations include receiving magnetic flux permeability measured by the magnetic transducer at a location on the portion and determining a coating thickness at the location based on the magnetic flux permeability measured at the location.

Abstract: To improve the usability so that the result of adjustment of a plurality of axes operating in cooperation is easily evaluated. An adjustment apparatus displays a graph indicating a temporal change of measurement data for each control axis and a control instruction on the same time base in a first area in a screen, and displays a control trajectory of a control position of each control axis, the control instruction, and a target trajectory of a target position in the screen.

Abstract: Systems and methods for authenticating material samples are provided. Digital images of the samples are processed to extract computer-vision features, which are used to train a classification algorithm. The computer-vision features of a test sample are evaluated by the trained classification algorithm to identify the test sample.

Abstract: Within a first image in a set of images comprising a panoramic view of a scene, a first boundary feature is identified using a model. Within the first boundary feature, a first set of points is selected. Within a second image in the set of images, a second boundary feature is identified using the model. Within the second boundary feature, a second set of points is selected. A set of parameters of a geometrical shape including the first set of points and the second set of points is determined. From the first image and the second image, a panoramic image is formed, the first image placed within the panoramic image according to the position of the first image on the geometrical shape, the second image placed in the panoramic image according to the position of the second image on the geometrical shape.

Abstract: A method is disclosed. The method includes receiving one or more images of bitmap data applied to a print medium as print medium image data, register the print medium image data to the bitmap data, detecting one or more candidate defects based on whether a difference between the print medium image data at a location and the bitmap data at the location exceeds a predetermined threshold, detecting one or more defects among the candidate defects and transmitting information about the one or more candidate defects classified as defects.

Abstract: In certain embodiments, a system for making an implant for an eye comprises a printer, a camera, and a computer. The printer prints material onto a target and has a printer head and printer controller. The printer head deposits the material onto the target, and the printer controller moves the printer head to deposit the material onto a specific location of the target. The camera generates an image to monitor the printing of the material. The computer stores a pattern for the implant, which is designed to provide refractive treatment for the eye; sends instructions to the printer controller to move the printer head to print the material onto the target according to the pattern; assesses the image from the camera according to the pattern; and adjusts the instructions in response to the image.

Abstract: A computer vision-based fastener loosening detection approach is described. A first image is captured at a first time and a second image is captured at a second time. A feature-based image registration is performed to create a third image. An intensity-based image registration is performed to create a fourth image. Registration errors are determined based on a comparison of the first and fourth images. A feature enhancement process is performed on the registration errors to determine whether the fastener has loosened between the first time and the second time.

Abstract: A system uses templates to generate data structures, for example, pipelines for deploying services in cloud based system. A template contains templating expressions used as placeholders for actual values. The generated data structure may be modified, for example, using an application. The system generates a reverse substitution map that associates actual values used in a data structure instance with a corresponding templating expression used as placeholders for the actual values. The system generates a modified version of the template for a modified version of the data structure by replacing actual values with the corresponding templating expressions from the reverse substitution map. The system can use the modified template to generate other instances of data structure that include the modifications made to the data structure.

Abstract: A method of manufacturing and analyzing a quality of an orthodontic aligner is described. An orthodontic aligner is manufactured by printing a mold associated with a dental arch of a patient based on a digital model of the mold, forming an orthodontic aligner over the mold, and trimming the orthodontic aligner. A quality of the orthodontic aligner is then assessed by imaging the orthodontic aligner to generate a first digital representation of the orthodontic aligner, comparing the first digital representation of the orthodontic aligner to a digital file associated with the orthodontic aligner, determining whether a cutline variation is detected between the orthodontic aligner and the digital file, and determining whether there is a manufacturing defect of the orthodontic aligner based on whether the cutline variation exceeds a cutline variation threshold.

Abstract: Provided is an analysis method for a crack rate of an electrode active material of an electrode, comprising the steps of: forming an electrode including an electrode active material, a binder, and a conductive material; impregnating the electrode with a resin and visualizing material regions including the electrode active material, the binder, and the conductive material which are included in the electrode, and a pore region; cutting the electrode and forming an electrode cross-section sample; photographing a cross section of the electrode cross-section sample using a scanning electron microscope and obtaining a cross-sectional image; performing primary image processing on the cross-sectional image and extracting total surface area pixels of the electrode active material; performing secondary image processing on the cross-sectional image and extracting total boundary pixels of the electrode active material; and calculating a crack rate of the electrode active material of the electrode in the cross-sectional i

Abstract: A spot detecting apparatus includes a photographing part and a spot detecting part. The photographing part photographs, in a first resolution, an image displayed on a display panel to output first resolution image data, and photograph, in a second resolution, the image displayed on the display panel to output second resolution image data, where the second resolution is higher than the first resolution, and the image displayed on the display panel includes a first spot greater than or equal to a reference size and a second spot less than the reference size. The spot detecting part receives the first resolution image data and the second resolution image data, and subtracts the first resolution image data from the second resolution image data to detect the second spot.

Abstract: The present invention discloses a ceramic ball automatic sorting system and method. The system automatically sucks a ceramic ball on a ceramic ball feeding track for image acquisition, identifies whether the ceramic ball is defective according to the acquired image information, and determines a ball storage device into which the ceramic ball is placed, and the whole process does not require manual participation, which achieves the automation of ceramic ball defect identification and sorting and improves the ceramic ball defect identification accuracy and sorting efficiency. According to the method, images of the ball surface shot at each angle are automatically spliced by using an automatic image splicing technology to achieve full coverage.

Abstract: Methods and systems for determining one or more alignment parameters for use in a process performed on a specimen are provided. One method includes determining measures of similarity between images generated by an imaging system for corresponding locations in each of two or more pairs of dies on a specimen and performing cluster analysis based on the determined measures of similarity to identify the images that are most similar to each other and to assign different subsets of the images that are most similar to each other to different die clusters, respectively. The method also includes separately determining one or more alignment parameters for two or more of the different die clusters. The one or more alignment parameters are used for aligning images generated by the imaging system for the specimen or another specimen to a common reference.