Abstract: A method of inspecting a component using an image retrieval module includes storing an inspection image file in a memory and identifying a region of interest in the inspection image file. The method further includes accessing a database storing image files and determining feature vectors associated with the image files. The method also includes determining a hash code for each image file based on the feature vectors and classifying a subset of image files as relevant based on the hash codes. The method further includes sorting the subset of image files based on the feature vectors and generating search results based on the sorted subset of image files. The image retrieval module includes a convolutional neural network configured to learn from the determination of the feature vectors and increase the accuracy of the image retrieval module in classifying the image files.

Abstract: Methods and systems may provide for technology to recognize features of current content to be shared by a current user, determine a plurality of platforms that allow access to data by other users and select one or more of the plurality of platforms to store the current content based on the recognized features.

Abstract: The present application concerns the visual identification of materials or documents for tracking or authentication purposes. It describes methods to automatically authenticate an object by comparing some object images with reference images, the object images being characterized by the fact that visual elements used for comparison are non-disturbing for the naked eye. In some described approaches it provides the operator with visible features to locate the area to be imaged. It also proposes ways for real-time implementation enabling user friendly detection using mobile devices like smart phones.

Abstract: To provide an image processing apparatus capable of correcting an orientation of a scanned image, even if the orientation of a document during scanning is incorrect. An image processing apparatus includes a document type determination unit configured to determine a document type of image data obtained by optical reading, a selection unit configured to select, based on a determination result from the document type determination unit, a determination algorithm to be applied, from a plurality of determination algorithms for determining an orientation of an image, and an orientation determination unit configured to determine an orientation of an image in the image data by using the determination algorithm selected by the selection unit.

Abstract: A Web-based system and method creates one or more qualitatively distinct process plans for machining a part. The surfaces of the part are modeled and parameters for a plurality of CNC machining tools are obtained, including the orientations along which the tool cuts away raw material. A maximal set of translations for each tool is also obtained, where each translation includes a collision-free orientation of the tool and a maximal machinable volume of material removable from the part in that orientation. A search engine navigates through a hierarchically-structured search space that starts at an initial state and transitions to successive states based on actions that satisfy a cost constraint function. Each state and each action includes a tool, orientation of the tool, and a maximal machinable volume. The search ends when a goal condition is satisfied. The actions constitute the process plan.

Abstract: In one embodiment, an apparatus comprises a storage device and a processor. The storage device stores a feature vector index, wherein the feature vector index comprises a sparse-array data structure representing a feature space for a set of labeled feature vectors, wherein the set of labeled feature vectors are assigned to a plurality of classes. The processor is to: receive a query corresponding to a target feature vector; access, via the storage device, a first portion of the feature vector index, wherein the first portion of the feature vector index comprises a subset of labeled feature vectors that correspond to a same portion of the feature space as the target feature vector; determine the corresponding class of the target feature vector based on the subset of labeled feature vectors; and provide a response to the query based on the corresponding class.

Abstract: Embodiments of a method and apparatus for generating a virtual avatar, a device and a storage medium are provided. The method may include: determining a template coefficient of a target face in a to-be-processed image based on at least two real face feature templates; and determining a virtual avatar of the target face according to the template coefficient and at least two virtual face feature templates associated with the at least two real face feature templates.

Abstract: A method for detecting a static logo of a video, an electronic apparatus and a storage medium. The method includes: calculating a pixel grayscale flag value, an edge gradient flag value and an edge direction flag value; calculating, in a preset neighborhood centered on the pixel at each pixel position of the current video frame, a first local confidence degree of the pixel grayscale flag value, a second local confidence degree of the edge gradient flag value, and a third local confidence degree of the edge direction flag value respectively; calculating a contribution score of each local confidence degree and a total contribution score of each pixel position; and gathering the total contribution score of each pixel position of the current video frame, and determining a static logo in the current video frame according to the total contribution score of each pixel position.

Abstract: Aspects of the disclosed technology provide a computational model that utilizes machine learning for detecting errors during a manual assembly process and determining a sequence of steps to complete the manual assembly process in order to mitigate the detected errors. In some implementations, the disclosed technology evaluates a target object at a step of an assembly process where an error is detected to a nominal object to obtain a comparison. Based on this comparison, a sequence of steps for completion of the assembly process of the target object is obtained. The assembly instructions for creating the target object are adjusted based on this sequence of steps.

Abstract: Applications under test (AUT) may be tested by automated testing systems utilizing machine vision to recognize visual elements presented by the AUT and apply inputs to graphical elements, just as a human would. By utilizing the smallest image patch available, processing demands of the testing system are minimized. However, the image patch used to identify a portion of an AUT must be identifiable to the automated system. By selecting image patches that comprise the smallest size, but can be identified in an AUT by an automated system using machine vision, even as the AUT display is resized, reproportioned, noisy, or otherwise altered from the testing platform that was utilized for training.

Abstract: A display apparatus includes a display screen, and a controller that causes the display screen to display a composite image in which a first image acquired by imaging a space by a camera and a second image representing at least one type of aerosol existing in the space are combined. The position of the at least one type of aerosol as seen in a depth direction in the first image is reflected in the second image.

Abstract: A method of training an image classification model includes obtaining training images associated with labels, where two or more labels of the labels are associated with each of the training images and where each label of the two or more labels corresponds to an image classification class. The method further includes classifying training images into one or more classes using a deep convolutional neural network, and comparing the classification of the training images against labels associated with the training images. The method also includes updating parameters of the deep convolutional neural network based on the comparison of the classification of the training images against the labels associated with the training images.

Abstract: Disclosed herein is a learning method of a neural network model for flame determination. The learning method of a neural network includes generating a learning image including a fake image generated by combining a real fire image and an arbitrary flame image with a background image; inputting the learning image to a first neural network model and outputting a determination result for whether a flame is present; and updating a weight in a layer extracting features of the learning image from the first neural network model using the determination result. According to the present invention, data of various fire situations may be secured, a performance of the neural network model that determines an occurrence of the fire through the secured data may be increased, and a quality of data for learning may be increased to allow the neural network model itself to predict various situations of fires.

Abstract: A position detection system includes a position detection apparatus and a server. The position detection apparatus includes an imaging apparatus that captures an image of an operation surface, a processor that detects a pointed position at which a pointing element is pointing on the operation surface by using a learned model based on captured images captured by the imaging apparatus, and a first communication apparatus that transmits the captured images to the server apparatus. The server apparatus includes at least one processor that detects a first image that does not contain an image of the pointing element out of the captured images, generates learning data containing the first image, and relearns the learned model by using the learning data.

Abstract: A system is provided for identifying consumer packaged goods (CPGs).

Abstract: The technology disclosed can provide capabilities to view and/or interact with the real world to the user of a wearable (or portable) device using a sensor configured to capture motion and/or determining the path of an object based on imaging, acoustic or vibrational waves. Implementations can enable improved user experience, greater safety, greater functionality to users of virtual reality for machine control and/or machine communications applications using wearable (or portable) devices, e.g., head mounted devices (HMDs), wearable goggles, watch computers, smartphones, and so forth, or mobile devices, e.g., autonomous and semi-autonomous robots, factory floor material handling systems, autonomous mass-transit vehicles, automobiles (human or machine driven), and so forth, equipped with suitable sensors and processors employing optical, audio or vibrational detection.

Abstract: A face authentication system including a storage to store a face image of each of a plurality of persons who are permitted to enter in advance and information on a zone; an image processing unit to detect a face of at least one person in an image captured by at least one camera having identification information, and generate a face cut-out image of the at least one person; a zone determination unit to determine a zone where a person in the face cut-out image is captured; a collation unit to collate the face cut-out image with the face image of each of the plurality of persons; and an output control unit to, when it is determined that there is not a face of a person appearing in the face cut-out image, superimpose a detection frame indicating a face of a person who is not permitted to enter the zone.

Abstract: A computer-implemented method for automatic template selection for extracting data from an input electronic document is provided. The method includes receiving a first set of candidate templates and an input electronic document. For each candidate template, a template similarity ratio value is calculated that represents a similarity of the candidate template to the input electronic document. The first set of candidate templates are ranked according to the template similarity ratios and then matched to the input electronic document resulting in generating a normalized similarity score for each particular candidate from among the candidate templates. Differences in normalized similarity scores of successive pairs of the candidate templates is determined and a breaking point is established. A second set of candidate templates is formed by selecting candidate templates that are ranked above the breaking point. Data from the input electronic document is extracted using the second set of candidate templates.

Abstract: A three-dimensional data generation device includes a virtual space arrangement section for arranging a virtual workpiece and a virtual vision sensor in a virtual space so that a part of the virtual workpiece fits in an imaging range of the virtual vision sensor, an arrangement relationship calculation section for calculating an arrangement relation between the arranged virtual workpiece and the virtual vision sensor, and a partial three-dimensional data generation section for generating partial three-dimensional data representing a partial shape of a workpiece which fits in the imaging range based on the calculated arrangement relationship.

Abstract: Method for receiving an input onto a graphical user interface at a client device, capturing an image frame at the client device, the image frame comprising a depiction of an object, identifying the object within the image frame, accessing media content associated with the object within a media repository in response to identifying the object, and causing presentation of the media content within the image frame at the client device.

Abstract: A drug inspection apparatus inspects drugs that are prepared based on prescription information and are packaged in a prescription bag. A drug database includes drug images of drugs that can be prepared. A comparison target selection section acquires drug images of drugs, which are prepared according to the prescription, and drugs similar thereto from the drug database. A first drug determination section compares captured images of prepared drugs with the drug images acquired from the drug database, and determines drugs present in the captured images and the number thereof. An inspection result determination section determines whether or not the prepared drugs and the number thereof match the prescription information based on the prescription information.

Abstract: This invention is a system and method for utilizing artificial intelligence to operate a surgical robot (e.g., to perform a laminectomy), including a surgical robot, an artificial intelligence guidance system, an image recognition system, an image recognition database, and a database of past procedures with sensor data, electronic medical records, and imaging data. The image recognition system may identify the tissue type present in the patient and if it is the desired tissue type, the AI guidance system may remove a layer of that tissue with the end effector on the surgical robot, and have the surgeon define the tissue type if the image recognition system identified the tissue as anything other than the desired tissue type.

Abstract: There is provided a method and a system configured obtain an image of a semiconductor specimen including one or more arrays, each including repetitive structural elements, and one or more regions, each region at least partially surrounding a corresponding array and including features different from the repetitive structural elements, wherein the PMC is configured to, during run-time scanning of the semiconductor specimen, perform a correlation analysis between pixel intensity of the image and pixel intensity of a reference image informative of at least one of the repetitive structural elements, to obtain a correlation matrix, use the correlation matrix to distinguish between one or more first areas of the image corresponding to the one or more arrays and one or more second areas of the image corresponding the one or more regions, and output data informative of the one or more first areas of the image.

Abstract: A face authentication apparatus includes a face image acquisition unit that acquires a face image of an authentication target, a collation unit that performs face authentication by calculating similarity between face information of the face image of the authentication target and reference face image of each registered user and comparing the similarity with a threshold, a prediction unit that predicts a change in the similarity on the basis of similarity history on authentication success, and a threshold change unit that changes the threshold on the basis of the prediction result.

Abstract: A method for verifying an image can include: acquiring a first feature point set of a source image and a second feature point set of a target image; determining a target local feature point pair based on the first feature point set and the second feature point set; determining a mapped point of the first feature point on the target image; determining a distance between a second feature point and the mapped point; acquiring a quantity of reference local feature point pairs; and determining that the target image is an image acquired by copying the source image based on the quantity being greater than a target quantity.

Abstract: A method for identifying and correcting fixed pattern noise includes capturing a focused image and an unfocused image via a variable focus lens. Fixed pattern noise represented in the unfocused image is filtered from the focused image. The unfocused image represents a low-pass filtered component of the focused image; subtracting the unfocused image from the focused image results in a high-pass and fixed pattern noise filtered focused image. Image capture and focus of the variable focus lens are synchronized to remove transitional frames from the image stream.

Abstract: According to at least one embodiment, a reading device includes a first device and a second device. The first device includes an imaging unit, a first recognition unit configured to recognize a commodity from a captured image of the imaging unit, and a voice output unit configured to emit a voice if the first recognition unit recognizes the commodity. The second device is separate from the first device, and includes a second recognition unit configured to recognize a commodity from the captured image by a method different from that of the first recognition unit and a second voice generation unit configured to output voice data for sounding the voice output unit if the second recognition unit recognizes the commodity.

Abstract: Embodiments for implementing enhanced ensemble model diversity and learning by a processor. One or more data sets may be created by combining one or more clusters of data points of a minority class with selected data points of a majority class. One or more ensemble models may be created from the one or more data sets using a supervised machine learning operation. An occurrence of an event may be predicted using the one or more ensemble models.

Abstract: The invention relates to a toy system including a plurality of toy construction elements, an image capturing device and a processor. The image capturing device is operable to capture one or more images of a toy construction model constructed from the toy construction elements. The processor is configured to: execute a digital game having computer executable code causing the processor to provide a digital play experience; receive an unlock code indicative of one or more virtual objects; unlock the one or more virtual objects for use in the digital play experience, each virtual object being associated with one of the respective toy construction elements or with a respective toy construction model; receive one or more images captured by said image capturing device; recognize one or more toy construction elements and/or toy construction models within the one or more images; provide a digital play experience involving said first unlocked virtual object.

Abstract: A document classification system uses an image file as a file of an image serving as a model for classifying a document to classify, by machine learning, an image read from a form as a document by a scanner of an image forming apparatus, and reports a classification failure image as an image of the document when the document is unsuccessfully classified.

Abstract: A motion detection method includes providing a buffer including a first buffer associated with a background image and a second buffer associated with a foreground image; checking first similarity between the gray level of an input pixel and the first gray level of the first buffer; determining the input pixel as a still pixel if the first similarity is true; checking second similarity between the gray level and the second gray level of the second buffer; determining the input pixel as a moving pixel if the second similarity is false; determining the input pixel as the moving pixel if the second count value is less than the first count value; and determining the input pixel as the still pixel and swapping the first buffer with the second buffer, if the second count value is not less than the first count value.

Abstract: Disclosed are methods, systems and apparatuses for creating an animal-shaped avatar using a human face. An avatar creation method according to example embodiments includes analyzing an image including a human face and automatically creating an animal-shaped avatar corresponding to the human face.

Abstract: Some embodiments are directed to an image processing apparatus comprising obtaining a reference image and a verification target image; selecting one or more defect detection processing from a plurality of types of defect detection processing for performing defect detection in the verification target image; executing the selected one or more defect detection processing on a difference image between the reference image and the verification target image in accordance with processing parameters of the selected one or more defect detection processing; and outputting a result display screen in which a defect in the verification target image and a defect detection processing used for detecting the defect can be identified, in a case where the defect is detected.

Abstract: Systems and methods of detecting and identifying objects are provided. In one exemplary embodiment, a method performed by one of a plurality of network nodes, with each network node having an optical sensor and being operable to wirelessly communicate with at least one other network node, comprises sending, by a network node over a wireless communication channel, to another network node, an indication associated with an object that is detected and identified by the network node based on one more images of that object that are captured by the optical sensor of the network node. Further, the detection and identification of the object is contemporaneous with the capture of the one or more images of that object. Also, the network node is operable to control a spatial orientation of the sensor so that the sensor has a viewing angle towards the object.

Abstract: Systems and methods for indexing geological features are disclosed. In one embodiment, a method for indexing geological features includes accessing a database storing a plurality of map objects that originate from documents. Each map object includes a map defined by a geographical boundary and a text caption. The method includes, for each map object, determining a plurality of geohashes within the geographical boundary, and includes, for each map object, comparing terms of the text caption with a list of geological keywords. For each map object, the method includes identifying one or more geological noun phrases within the text caption that match one or more geological noun phrases of the list. The method includes determining, for each geological noun phrase, one or more geohashes associated with the geological noun phrase and, for each geohash, determining a frequency that the geohash is associated with the geological noun phrase.

Abstract: A method, system and computer-usable medium for performing cognitive computing operations comprising receiving streams of data from a plurality of data sources; processing the streams of data from the plurality of data sources, the processing the streams of data from the plurality of data sources performing data enriching for incorporation into a cognitive graph; defining a travel-related cognitive persona within the cognitive graph, the travel-related cognitive persona corresponding to an archetype user model, the travel-related cognitive persona comprising a set of nodes in the cognitive graph; associating a user with the travel-related cognitive persona; defining a travel-related cognitive profile within the cognitive graph, the travel-related cognitive profile comprising an instance of the travel-related cognitive persona that references personal data associated with the user; associating the user with the travel-related cognitive profile; and, performing a cognitive computing operation based upon the tra

Abstract: An inspection device that inspects eligibility of a subject image, the inspection device including a hardware processor and a recording medium including instructions that when executed by the hardware processor cause the inspection device to: acquire the subject image and a reference image corresponding to the subject image; acquire a judgment criterion indicating a range of eligibility for differences between images; detect a difference between the subject image and the reference image; and when the difference is detected, judge eligibility of the subject image by determining whether or not the difference is included in the range indicated by the judgment criterion.

Abstract: Information recommendation methods are provided. Image information corresponding to an image is obtained by processing circuitry. The image is associated with a user identifier. A user tag set corresponding to the user identifier and the image information is generated. A feature vector corresponding to user tags in the user tag set and the image information is formed. The feature vector is processed according to a trained information recommendation model, to obtain a recommendation parameter of to-be-recommended information. A recommendation of the to-be-recommended information is provided to a terminal corresponding to the user identifier according to the recommendation parameter.

Abstract: A non-transitory computer readable medium that stores instructions that once executed by a computer cause the computer to execute the stages of: calculating a first function that represents an object that is three dimensional; calculating a second function that is a convolution or an approximated convolution of (a) the first function applied on points of the object, and (b) an other function that is the first function composed with a function that sends points of the object to opposite points; wherein the second function is translation invariant; and calculating the translation and rotation invariant features of the query object, based on the second function.

Abstract: A vision system for a vehicle includes a camera and an electronic control unit (ECU) with an image processor. The ECU generates a reduced resolution frame of captured image data and the ECU determines a reduced resolution detection result based on pedestrian detection using the reduced resolution frame of captured image data. The ECU, responsive to processing by the image processor of image data, generates a cropped frame of captured image data and the ECU determines a cropped detection result based on pedestrian detection using the cropped frame of captured image data. Responsive to determining the reduced resolution detection result and determining the cropped detection result, the ECU merges the reduced resolution detection result and the cropped detection result into a final pedestrian detection result. The final pedestrian detection result is indicative of presence of a pedestrian within the field of view of the camera.

Abstract: This system is designed to color correct a targeted color or colors in a video stream comprising: a computer device having a computer readable medium; and, a set of computer readable instructions embodied on the computer readable medium that are configured to: receive a dataset that includes one or more pairs of video frames where a first frame of the pair of an incorrect color frame and the second frame of the pair is a color correct frame, using a machine learning module to create a mask according to the dataset, receiving an image, correcting the image, and, transmitting the corrected image to a display.

Abstract: The system has a form analysis module that receives an image of a form into which values have been filled for the possible fields of information on the form, such as first name, address, age, and the like. By using a library of form templates, a form analysis module allows both flexibility of form processing and simplicity for the user. That is, the techniques used by the form analysis module allow the processing of any form image for which the library has a form template example. The form image need not precisely match any form template, but rather may be scaled or shifted relative to a corresponding template. Additionally, the user need only provide the form image itself, without providing any additional exemplars, metadata for training, or the like.

Abstract: A method for generating a holographic image, a signal processor, a holographic image display device, a wearable apparatus, and an onboard head-up display apparatus. The method comprises: performing holographic transformation on the basis of a target amplitude phase distribution of a target image to obtain a holographic phase image; performing phase quantization of the holographic phase image to obtain a quantized holographic image; performing inverse holographic transformation of the quantized holographic image to obtain a reconstructed image; if the reconstructed image satisfies a preset condition, determining that the quantized holographic image is a target holographic image; if not, constraining the amplitude phase of the reconstructed image and, on the basis of the amplitude phase constrained image, continuing iteration.

Abstract: A method comprises displaying a plurality of items to a user on a first page on a display screen of an electronic device. Each item of the plurality of items displayed on the first page is classified according to whether an item is of interest to the user viewing the display screen. A correlation factor between the user and each item classified as of interest to the user is determined. The method also includes, for at least the first one of the plurality of items determined to have a correlation factor above a predetermined threshold, identifying detailed information about a first one of the plurality of items. The identified detailed information about a first one of the plurality of items is automatically displayed. The identified detailed information is displayed without receiving an input indicating a selection of a first one of the plurality of items from a hand-operated input device.

Abstract: An active three-dimensional scene information acquisition method based on dimensionality-reduced sparse representation is provided. The method jointly processes multiple one-dimensional active detection signals collected synchronously to achieve three-dimensional positioning of objects in a detected scene or three-dimensional reconstruction of a scene structure. Through an active detection system equipped with one transmitter and multiple receivers, simultaneous three-dimensional positioning of multiple targets in a scene or three-dimensional reconstruction of the geometry of the scene is achieved.

Abstract: In order to ensure that similarity is detected with high accuracy, regardless of the types of images constituting a group of images to be evaluated for similarity, the image processing device includes difference calculation means 11 for deforming one of two or more images constituting an image group in one or more deforming ways, and calculating a degree of difference between the deformed image and the other image or images in the image group for each pixel using multiple ways for similarity evaluation, normalization means 12 for normalizing each degree of difference by each of the multiple ways for similarity evaluation, and difference integration means 15 for integrating normalized degrees of difference.

Abstract: Systems and methods capable of initializing centroids in large datasets before commencement of clustering operations. The systems and methods can utilize a random sampling window to increase the speed of centroid initialization. The systems and methods can be modified to leverage parallelism and be configured for execution on multi-node compute clusters. Optionally, the initialization systems and methods can include post-initialization centroid discarding and/or re-assignment operations that adaptively control cluster sizes.

Abstract: A method and system for image processing are provided in the present disclosure. The method may include obtaining a plurality of source images generated by a plurality of imaging sensors. The method may also include processing each of the plurality of source images by: retrieving a plurality of source image blocks from the source image according to block position information associated with the corresponding imaging sensor; generating, for each of the plurality of source image blocks, a target image block based on the source image block; and forming a target image based on the generated target image blocks. The method may further include generating a combined image based on the target images.

Abstract: Methods, systems, and related products that provide enhanced broadening and narrowing navigation capabilities through visualized populations of items, such as media content items. Aspects of the disclosure relate to methods of identifying a population of items and groupings of those items for visualizing, via a graphical interface, in a meaningful and easily navigable configuration. Aspects of the present disclosure relate to pre-selection interactions with visualized populations to explore potential narrowing or broadening navigation actions, and selection interactions for performing a narrowing or broadening navigation.

Abstract: In some embodiments, a process and system are provided for generating a user interface for classification of a sample image of a cell that includes receiving a sample image of a sample particle from a biological sample and selecting reference images that each portray a reference particle of a biological sample. The reference images can be ordered based on similarity and the reference images can be selected based on the order. The first selected reference image can be aligned with the sample image and expanded such that the adjacent edges of the reference image and sample image are the same. The expanded image can be dynamically filled. The sample image and the expanded reference image can be displayed in a user interface.