Abstract: Provided are an image discrimination apparatus, an image discrimination method, a program of the image discrimination apparatus, and a recording medium on which the program is stored, for relatively simply discriminating between “a person image” and “a non-person image” in consideration of an intention of an album maker or the like. A user sets a reference value for a reference item by adjusting a position of a slide on a slide bar. In a case where the reference value is set at a position P11, a discrimination target image I11 is discriminated as a person image, but discrimination target images I12 and I13 are discriminated as non-person images. In a case where the reference value is set at a position P12, the discrimination target images I11 and I12 are discriminated as person images, and the discrimination target image I13 is discriminated as a non-person image.

Abstract: A method includes: recording an image at a sensor block, the sensor block; detecting a set of objects in the image based on an object classification model; generating a feature vector for the image based on the set of objects; accessing a workstation template for the work area, the workstation template defining a set of default objects for each workstation in the work area; identifying a subset of objects comprising an intersection of the set of default objects and the set of objects; removing the subset of objects from the feature vector; accessing an occupancy template for the work area, the occupancy template defining a set of significant objects; classifying the workstation as occupied based on the feature vector and the set of significant objects; and rendering a representation of the workstation at a work area interface, the representation indicating occupancy of the workstation.

Abstract: Embodiments of the disclosure provide a method for generating a dynamic image, an electronic device for the same and a storage medium for the same. The electronic device obtains a video based on a trigger operation. The electronic device obtains images of the video by separating the images an audio data of the video. The images include first images and second images. The electronic device obtains target images by processing the first images. Each of the target images does not contain the target object. The electronic device generates the dynamic image based on the images and the target images.

Abstract: Techniques and systems are provided for light estimation. In some examples, a system receives a plurality of frames associated with a scene. The plurality of frames includes a first frame and a second frame occurring after the first frame. The system determines, based on image data of the first frame, a first light estimate associated with the scene. The system also determines, based on image data of the second frame, a second light estimate associated with the scene. The system further generates an aggregate light estimate associated with the scene based on combining the second light estimate with at least the first light estimate.

Abstract: A method for product compliance includes receiving, at data processing hardware, a planogram defining a representative placement of a product on a display shelf and receiving at least one image from an imaging device having a field of view arranged to capture a top surface of the display shelf. The method also includes determining whether the product is disposed on the display shelf based on the at least one image. When the product is disposed on the display shelf, the method includes determining an actual placement of the product on the display shelf and comparing the actual placement of the product to the representative placement of the product defined by the planogram. The method further includes determining a planogram compliance based on the comparison of the actual placement of the product to the representative placement of the product and communicating the planogram compliance to a network.

Abstract: Systems and methods for iris authentication are disclosed. In one aspect, a deep neural network (DNN) with a triplet network architecture can be trained to learn an embedding (e.g., another DNN) that maps from the higher dimensional eye image space to a lower dimensional embedding space. The DNN can be trained with segmented iris images or images of the periocular region of the eye (including the eye and portions around the eye such as eyelids, eyebrows, eyelashes, and skin surrounding the eye). With the triplet network architecture, an embedding space representation (ESR) of a person's eye image can be closer to the ESRs of the person's other eye images than it is to the ESR of another person's eye image. In another aspect, to authenticate a user as an authorized user, an ESR of the user's eye image can be sufficiently close to an ESR of the authorized user's eye image.

Abstract: A method for maintaining inventory within a store includes: accessing an image (e.g., a color image, depth image) depicting an inventory structure; detecting a slot region of the image depicting a slot; identifying a product type assigned to the slot; accessing a product dimension of the product type; defining a target region within the slot in the image based on the product dimension; defining a product region within the slot in the image based on the product dimension and the target region; defining a back-of-shelf plane intersecting the target region of the image; detecting a surface within the product region; and, in response to the surface intersecting the back-of-shelf plane, identifying the slot as empty and generating a prompt to restock the slot with product units of the product type.

Abstract: A method for providing similar or related products based on deep-learning, which is performed by a data processing unit of a shopping mall server, includes: acquiring an item image and item information for an item registered in a shopping mall; detecting bounding boxes for one or more objects by object-detecting the item image; setting a bounding box for an object associated with the item based on the item information; creating a main bounding box image by cropping a portion of the item image in the set bounding box; creating a padding image by padding-processing the main bounding box image; extracting a feature vector for the padding image; matching the feature vector with the item and storing the feature vector in a database; and creating the database for a similar or related product search service.

Abstract: Method for selecting an elastic venous restraint orthosis intended to be slipped onto a lower limb of a patient. Acquisition of a photograph representing the skin of the limb and a calibration map including one or more calibration zones. The calibration map is placed on the limb in a position termed the “acquisition position.” Calibration of the photograph by the calibration zone or zones, in such a way that the representation of the skin on the photograph exhibits a calibrated colour. Selection, as a function of the calibrated colour, by computer and from a set of colours of a tone chart, of a tone chart colour, preferably of the tone chart colour closest to the calibrated colour, termed the “optimal colour,” and then determination, by computer, of an orthosis colour as a function of the tone chart colour selected. Selection of an orthosis exhibiting the orthosis colour.

Abstract: A system for detecting and tracking objects using lidar can include one or more processors configured to receive lidar data. The one or more processors can determine shape data from the lidar data. The shape data can be indicative of an object. The one or more processors can determine a plurality of extents of the object based on the shape data. The one or more processors can update a state of the object based on the plurality of extents, the state including a boundary of the object. The one or more processors can provide the state of the object to an autonomous vehicle controller to cause the autonomous vehicle controller to control an autonomous vehicle responsive to the state of the object.

Abstract: In one embodiment, a method includes receiving sensor data of an environment of the vehicle generated by one or more sensors of the vehicle, the sensors comprising a camera, identifying, based on the sensor data, one or more objects in a field of view of the camera and one or more object types that correspond to the one or more objects, determining one or more target histograms that correspond to the object types, generating a processed image based on an image captured by the camera, wherein the processed image has a histogram based on the target histograms, and using the processed image to determine state information associated with the objects. The processed image may be generated by processing the image captured by the camera using a histogram matching algorithm to generate the histogram of the processed image based on the target histograms.

Abstract: A method for identifying a logo within at least one image includes identifying an area containing the logo within the at least one image, extracting logo features from the area by analyzing image gradient vectors associated with the at least one image, and using a machine learning model to identify the logo from the extracted logo features, wherein the machine learning model is trained to identify at least one target logo based on a received image data containing the logo features.

Abstract: Embodiments of the invention utilize a feature-extraction approach and/or a matching approach in combination with a nonparametric approach to estimate the proportion of documents in each of multiple labeled categories with high accuracy. The feature-extraction approach automatically generates continuously valued text features optimized for estimating the category proportions, and the matching approach constructs a matched set that closely resembles a data set that is unobserved based on an observed set, thereby improving the degree to which the distributions of the observed and unobserved sets resemble each other.

Abstract: Personal equipment detection may utilize pose-based detection. Input image data may be evaluated to detect persons in the image data. For detected persons, regions of the persons may be determined. Personal equipment may be detected for the detected persons in the image data and compared with the regions of the persons to determine whether the detected personal equipment is properly placed on the person.

Abstract: A portable terminal includes an extraction unit and a display control unit. The extraction unit extracts a part of a display image displayed on a touch panel display, as an extraction image used as a compositing target image. The display control unit, in a case where a plurality of regions having different areas are included in the extraction image used as the compositing target image, removes at least one of the plurality of regions in order of area based on an operation amount of an operation input by a user.

Abstract: An electronic device and method for human skin detection based on a human body-prior is provided. A color image of a person is acquired, and a 3D body model of the person is estimated based on the color image. One or more unclothed parts of the 3D body model are identified. The one or more unclothed parts correspond to one or more body parts, of which at least a portion of skin remains uncovered by clothes. From the color image, pixel information corresponding to the one or more unclothed parts is extracted and classification information is determined based on the pixel information. The classification information includes a set of values, each indicating a likelihood of whether a corresponding pixel of the color image is part of an unclothed skin portion of the person. The unclothed skin portion is detected in the color image based on the classification information.

Abstract: According to embodiments of the present disclosure, methods of and computer program products for operating a plurality of classifiers are provided. A plurality of input entities are read, each input entity having an associated target label. The input entities are provided to a first classifier, and a category of each input entity is obtained therefrom. A feature map is determined for each input entity. Each feature map is provided to each of a set of classifiers, and an assigned label is obtained for each feature map from each of the set of classifiers. Each classifier is associated with one of the categories. For each classifier, the assigned label for each feature map is compared to the target labels to determine a plurality of gradients. The plurality of gradients are masked according to each category, yielding a masked set of gradients for each category. Each classifier is trained according its associated masked gradients.

Abstract: A system and method for providing payments is disclosed. A method can include establishing a wireless link between a mobile device and a merchant device. After an instruction is displayed on the mobile device, a combination of a first type of input and a second type of input are received on the mobile device, first type of input including at least one button press of a physical button and the second type of input received from a user to confirm a payment for the purchase. Based on the inputs, payment data is retrieved from a memory of the mobile device. The method includes receiving the payment data at the merchant device to make the purchase, wherein receiving the payment data, via the wireless link, at the merchant device to make the purchase is performed according to a protocol for communicating the payment data to the merchant device.

Abstract: A system and method for providing payments is disclosed. A method can include establishing a wireless link between a mobile device and a merchant device. After an instruction is displayed on the mobile device, a combination of a first type of input and a second type of input are received on the mobile device, first type of input including at least one button press of a physical button and the second type of input received from a user to confirm a payment for the purchase. Based on the inputs, payment data is retrieved from a memory of the mobile device. The method includes receiving the payment data at the merchant device to make the purchase, wherein receiving the payment data, via the wireless link, at the merchant device to make the purchase is performed according to a protocol for communicating the payment data to the merchant device.

Abstract: A system for facilitating e-commerce transaction is disclosed. The system includes a request receiving module to enable the interactive support agent platform to receive order requests from a customer. The system includes an order placement module to identify a merchant from a merchant database based on the order requests corresponds to the customer specific merchandise or service request and enable the interactive support agent platform to select products from a catalogue of an identified merchant based on the order requests. The system includes a checkout processing module to enable the interactive support agent platform to share a checkout page with the customer via a communication medium based on selected products corresponds to the identified merchant and perform a checkout process by transmitting billing and shipping information via a secure checkout page rendered within a chat window, a browser or the user interface corresponding to the interactive support agent platform.

Abstract: A method of detecting frames in a video that demarcate a pre-determined type of video segment within the video is provided. The method includes identifying visually distinctive candidate marker frames within the video, grouping the candidate marker frames into a plurality of groups based on visual similarity, computing a collective score for each of the groups based on temporal proximity of each of the candidate marker frames within the group to related events occurring within the video, and selecting at least one of the groups based on the collective proximity scores as marker frames that demarcate the pre-determined type of video segment. A video processing electronic device and at least one non-transitory computer readable storage medium having computer program instructions stored thereon for performing the method are also provided.

Abstract: Methods, an apparatus, and software media are provided for removing unwanted information such as moving or temporary foreground objects from a video sequence. The method performs, for each pixel, a statistical analysis to create a background data model whose color values can be used to detect and remove the unwanted information. This includes determining a prevalent color cluster from among k clusters of color values for the pixel in successive frames. The method uses k-means clustering. To replace the unwanted information, the method iterates frames to find frames in which a pixel's color value is not included in the prevalent color cluster. In those frames, it replaces the pixel's color value with a value from the prevalent color cluster.

Abstract: There are provided systems and methods for dynamically rendered interface elements during online chat sessions. A user may engage in online communications with another user, such as a communication session between a customer and a customer representative or agent of a merchant. During this communication session, the agent may navigate to particular data on the agent's device, which may be desirable to provide to the customer. For example, the agent may view a particular item of interest to the customer. An application programming interface of the merchant may detect one or more actions or calls associated with this data and may dynamically provide an interface element to transmit data displayed on the agent's device to the customer's device during the communication session. The customer may view a dynamically rendered interface element that allows for processing data during the communication session with the agent.

Abstract: The present invention discloses a system for automated vehicles license plates characters segmentation and recognition comprising an imaging processor connected to at least one image grabber module or camera. The image grabber module captures images of the vehicles and forwards it to said connected imaging processor and the imaging processor segments and recognizes the vehicles license plates character region including the region with deformed license plates characters in the captured vehicle images by involving binarization of maximally stable external regions corresponding to probable license plate region in the captured vehicle images.

Abstract: A processor obtains an input image containing both bright and dark regions. The processor obtains a threshold between a first pixel value and a second pixel value of the display. Upon detecting a region of the input image having an original pixel value above the threshold, the processor can create a data structure including a location of the region in the input image and an original pixel value of the region. The data structure occupies less memory than the input image. The display presents the input image including the region of the image having the original pixel value above the threshold. The processor sends the data structure to a camera, which records the presented image. The processor performing postprocessing obtains the data structure and the recorded image and increases dynamic range of the recorded image by modifying the recorded image based on the data structure.

Abstract: A verifiable display is provided that enables the visual content of the display to be detected and confirmed in a variety of ambient lighting conditions, environments, and operational states. In particular, the verifiable display has a display layer that is capable of visually setting an intended message for human or machine reading, with the intended message being set using pixels. Depending on the operational condition of the display and the ambient light, for example, the message that is actually displayed and perceivable may vary from the intended message. To detect what message is actually displayed, a light detection layer in the verifiable display detects the illumination state of the pixels, and in that way is able to detect what message is actually being presented by the display layer.

Abstract: A method for controlling a terminal apparatus includes acquiring a first gesture image; determining a central coordinate of a gesture in the first gesture image; determining a controlling range in which the gesture has control over the terminal apparatus, based on the central coordinate of the gesture in the first gesture image; and controlling a control object in the controlling range to execute an operation based on a control instruction corresponding to the gesture.

Abstract: A system for processing encoded image components for artificial intelligence tasks. The system can include one or more compute units, one or more controllers and memory. The one or more controllers can include one or more micro-op schedulers and one or more channel switches. The one or more compute units can be configured to process components of the transformed domain image data according to one or more micro-operations for an artificial intelligence task. The one or more channel switches can be configured to selectively control the transfer of the components of transformed domain image data to the one or more compute units based on one or more gating flags. The one or more channel switches can also be configured to selectively control generation of the one or more micro-operations by the one or more micro-op schedulers based on the one or more gating flags.

Abstract: An in-memory graph query runtime is integrated inside a database management system and is capable of performing simple patter-matching queries against homogeneous graphs. The runtime efficiently combines breadth-first (BFS) and depth-first (DFS) neighbor traversal algorithms to achieve a hybrid runtime that takes the best from both sides. As a result, the hybrid runtime is able to process arbitrarily large queries with a fixed amount of memory, optimizing for memory locality.

Abstract: An apparatus includes: a display control unit that displays a UI screen for performing a predetermined process, the UI screen being a screen where unit blocks each assumed as a single continuous character string in a scan image are displayed to be selectable by the user; an OCR process unit that performs an OCR process on unit blocks selected by the user through the UI screen to thereby extract character strings; and a setting unit that sets incidental information for the predetermined process by using the character strings extracted by the OCR process unit. The display control unit separates a character string satisfying a predetermined separation condition among the character strings extracted by the OCR process unit from the unit blocks selected by the user, and displays the separated character strings on the UI screen such that the separated character strings are selectable by the user.

Abstract: An information processing device (100) includes a memory and processing circuitry. The memory stores a data set (DG) including multiple items of digital data (DD) and a label set (RG) including multiple labels. Each of the multiple labels are added to each of the multiple items of digital data (DD). The processing circuitry generates a feature vector set (BG) by extracting a predetermined feature from each of the multiple items of digital data (DD) and generating feature vectors indicating the extracted features. The feature vector set includes the feature vectors. The processing circuitry determines homogeneity of the data set (DG) by performing a trial of supervised clustering on the feature vector set (BG) by using the label set (RG) and determining the possibility of the clustering.

Abstract: Systems, methods, and articles of manufacture for an internal private online marketplace are presented. Some embodiments described herein may include a method which may involve (1) identifying one or more items listed in one or more databases, and (2) generating a transfer protocol between the destination entity that desires to possess the one or more items with that of the source entity that possesses or has responsibility over the one or more items. The desired items may be identified by characteristics. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: A system includes one or more memory devices storing instructions, and one or more processors configured to execute the instructions to perform the steps of a method to automatically crop images. The system may convert a raw image into a grayscale image before applying an edge detection operator to the grayscale image to create an edge image. The system may then create a binary image based on the edge image, identify one or more contours in the binary image, and determine one or more contour bounding image areas surrounding the contour(s). Upon identifying contour bounding image area(s) having user-specified dimensional criteria, the system may determine a minimum bounded image area including those area(s), pad the minimum bounded image area, and crop the raw image based on the padded bounded area.

Abstract: A data ingestion system normalizes ingested documents and extracts data based on a template that is applied to the documents. In an aspect, the system accesses a document of a document type and determines a template to apply to the document. The system normalizes the document, extracts data values from the document based at least in part on the template, and generates structured data based at least partly on the extracted data.

Abstract: 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.

Abstract: An apparatus and a method for generating a high-quality one point color image are provided. A composite image generation unit that generates a composite image by executing composition processing using a color image and a monochrome image captured from different viewpoints, and an output image generation unit that generates a one point color image in which only a partial area of the image is colored are included. The output image generation unit generates a one point color image in which a colorization area in the one point color image is set as an area to which pixel values of the composite image are output, and a non-colorization area is set as an area to which pixel values of the monochrome image are output. The colorization area is selected by either user selection or automatic selection. For example, user-specified area information, subject distance information, and the like are used for the execution.

Abstract: A method for identifying objects includes generating a feature vector of an unknown object from an image of an environment. The method also includes comparing the feature vector of the unknown object to feature vectors of known objects. The method further includes determining whether a similarity between the feature vector of the unknown object and the feature vector of one of the known objects satisfies a threshold. Furthermore, the method includes identifying the unknown object based on the determination.

Abstract: A method for registering an imaging detector to a surface projects and records a sequence having a first sparse pattern of lines followed by a second sparse pattern of lines. A first subset of positions receives lines from both first and second sparse patterns corresponding to a first label. A second subset of positions receives only lines from the first sparse pattern corresponding to a second label. A third subset of positions receives only lines from the second sparse pattern corresponding to a third label. The first, second, and third labels are decoded and each member element of the first, second, and third subsets of positions registered to the imaging detector according to the decoded labels. One or more dense patterns of lines positionally correlated with registered member elements of the decoded labels are projected and recorded. An image of the surface contour is formed according to the recorded pattern.

Abstract: Disclosed are systems, methods, and computer-readable storage media to enhance an image on a mobile computing device. In some aspects, a user interface on the mobile computing device provides a plurality of image filters, each of the image filters associated with a different replacement sky type. Upon application of one of the plurality of image filters to an image, the mobile computing device is configured to identify a sky portion of the image, modify a color mapping of a non-sky portion of the image, and replace the sky portion of the image with replacement sky data corresponding to the applied image filter.

Abstract: Various implementations for object detection include a method includes capturing a video stream that includes an activity object and a pointing object, identifying the activity object, displaying a graphical user interface embodying a virtual scene based on the identified activity object, determining a location of the pointing object relative to the activity object, determining a routine based on the location of the pointing object relative to the activity object, and executing the routine within the virtual scene.

Abstract: The disclosed embodiments include a method performed by a data intake and query system. The method includes populating each metric including a measure value, cataloging metadata in an in-memory metrics catalog, where the metadata is related to the metrics. The method further includes receiving a search query including search criteria, evaluating the search query by applying the search criteria to the metadata of the metrics catalog to obtain results that satisfy the search criteria, and causing display, on a display device, of the results or data indicative of the results.

Abstract: A method includes identifying a first geometric pattern that failed a design rule check, identifying a second geometric pattern that passed the design rule check, morphing the first geometric pattern based on the second geometric pattern to generate a morphed geometric pattern, wherein the morphed geometric pattern passes the design rule check, and replacing the first geometric pattern with the morphed geometric pattern.

Abstract: A system for presenting video signals related to a marker image on a surface of a sports ball structured by a plurality of panels includes a computing device having a camera, and a server linked to the computing device via internet, the server being arranged to store the video signals related to the maker image, wherein programs running on the computing device includes the steps to obtain the maker images captured by the camera, extract a digital watermark embedded from the marker image, the digital watermark being positioned on a part of a curved surface of the plurality of panels formed by sewing, access the server to search the video signals corresponding to information in the digital watermark, receive the video signals from the server; and display the received video signals on the display in the computing device.

Abstract: An IoT based apparatus to assess the quality of food or agricultural produce is disclosed. The apparatus comprises a frame having an enclosure, a movable tray disposed at a middle portion of the enclosure, one or more camera installed within the enclosure, one or more light source strategically mounted within the enclosure to avoid reflection and hot spots, at least one storage unit, a touch screen display and a single board computer coupled to the camera, light source, storage unit and touch screen display. The enclosure is illuminated by the light source and the camera is configured to capture the image of the produce from both the top and bottom side of the produce. A pre-trained deep learning model is used on both the top and bottom view images to identify defects in the agricultural produce. The identified defects are displayed to the user via the touch screen display.

Abstract: An approach to place recognition from an image makes use of the detection of objects at a set of known places as well as at an unknown place. Images of the detected objects in an image of the unknown place are processed to yield respective numerical descriptors, and these descriptors are used to compare the unknown place to the known places to recognize the unknown place. At least some embodiments make use of a trained parameterized image processor to transform an image of an object to an object descriptor, and the training of the processor is meant to preserve distinctions between different instances of a type of object, as well as distinctions between entirely different types of objects.

Abstract: A transmission device includes an image processing unit that controls transmission of a first packet including region information regarding a region detected from an image and controls transmission of a second packet for each of lines in which at least the region has been detected in the image. The second packet comprises a header including information regarding the line, and a payload including region data concerning a partial region corresponding to the line, out of the region, in which the header includes: identification information of the data included in the payload; an error correction code of the information included in the header; and an extension region provided so as to be interposed between the identification information and the error correction code, and information indicating whether or not the region data is included in the payload corresponding to the header is set in at least a part of the extension region.

Abstract: Disclosed are methods, systems, and non-transitory computer-readable medium for analysis of images including wearable items. For example, a method may include obtaining a first set of images, each of the first set of images depicting a product; obtaining a first set of labels associated with the first set of images; training an image segmentation neural network based on the first set of images and the first set of labels; obtaining a second set of images, each of the second set of images depicting a known product; obtaining a second set of labels associated with the second set of images; training an image classification neural network based on the second set of images and the second set of labels; receiving a query image depicting a product that is not yet identified; and performing image segmentation of the query image and identifying the product in the image by performing image analysis.

Abstract: Systems and methods of video inpainting for autonomous driving are disclosed. For example, the method stitches a multiplicity of depth frames into a 3D map, where one or more objects in the depth frames have previously been removed. The method further projects the 3D map onto a first image frame to generate a corresponding depth map, where the first image frame includes a target inpainting region. For each target pixel within the target inpainting region of the first image frame, based on the corresponding depth map, the method further maps the target pixel within the target inpainting region of the first image frame to a candidate pixel in a second image frame. The method further determines a candidate color to fill the target pixel. The method further performs Poisson image editing on the first image frame to achieve color consistency at a boundary and between inside and outside of the target inpainting region of the first image frame.

Abstract: A method of detecting objects located in an environment around a vehicle, comprises the steps of obtaining a 2D image of a scene from an image capture device fitted to the vehicle, generating a set of particles that each comprise a set of parameters that define the state of at least one object that may be present in the scene, calculating an edge strength and edge direction for each pixel of the captured 2D image; and for each particle in the set: generating a 3D probabilistic model of the object that is associated with the particle, the model defining a set of edges of the object, each edge in the model defined by at least one likelihood function defining a probabilistic distribution of at least one characteristic of the edge, mapping the likelihood functions of the probabilistic model into the 2D plane of the captured image as a function of the parameters of the particle; and processing the edge strength and edge direction values with the probability values to determine the likelihood that the particle defi

Abstract: An electronic device obtains a collection of images, where each image in the collection of images is associated with a first set of scores. The set of first scores includes text descriptors associated with each image. The electronic devices obtains a media item associated with a second score. The second score is associated with each respective text descriptor of the set of text descriptors. The electronic device then selects a subset of the collection of images based on the first set of scores and the second set of scores. The electronic device concurrently presents a respective image of the subset of the collection of images and the media item.