Abstract: An object identification method and a mobile terminal are provided. The object identification method includes: capturing a scan object through the camera in a first operating state, in a case that a screen of the mobile terminal is turned off, to obtain a first capturing result; controlling the camera to enter a second operating state in a case that the scan object is determined to meet a preset condition according to the first capturing result, capturing the scan object through the camera in the second operating state to obtain a second capturing result, recognizing the scan object according to the second capturing result, and controlling the mobile terminal to turn on the screen to display a recognition result corresponding to the scan object.

Abstract: A computer-implemented method for computing a prediction on images of a scene includes: receiving one or more polarization raw frames of a scene, the polarization raw frames being captured with a polarizing filter at a different linear polarization angle; extracting one or more first tensors in one or more polarization representation spaces from the polarization raw frames; and computing a prediction regarding one or more optically challenging objects in the scene based on the one or more first tensors in the one or more polarization representation spaces.

Abstract: A feature of a subject file is identified. The feature is compared to a historical feature of a historical file. A similarity between the subject file and the historical file is calculated based on the comparing. A historical success metric for the historical file is identified. An intensive text extraction success value for the subject file is calculated based on the similarity and the historical success metric. Based on the intensive extraction success value, whether an intensive text extraction method should be performed on the subject file is determined.

Abstract: Methods and systems for analysis of image data generated from various reference points. Particularly, the methods and systems provided are useful for real time analysis of image and sequence data generated during DNA sequencing methodologies.

Abstract: A candidate face image and attribute information of each imaging attribute item are acquired. For each imaging attribute item, attribute information is extracted from a database that stores attribute information that has a degree of participation in false authentication greater than a participation degree threshold, among attribute information of analyzed imaging attribute items of analyzed master face images that resulted in false authentication in face image authentication. For each imaging attribute item, whether or not the extracted attribute information has a similarity to the acquired attribute information of the each imaging attribute item greater than a similarity threshold is determined. For each imaging attribute item for which the similarity is greater than the similarity threshold, a weight is assigned. A total score is calculated by summing the weights. When the total score satisfies a predetermined threshold value, the candidate face image is determined as inappropriate as a master face image.

Abstract: A verification method and a verification apparatus based on an attacking image style transfer are provided. The method includes the following steps. A style transfer is performed on a verification image for verifying an identity, so as to generate multiple stylized images having at least one style, in which the style transfer includes modifying a local pattern of the verification image while retaining a global pattern of the verification image. At least one of the verification image and the stylized images is processed to add an interference signal having at least one specific pattern for interfering with image recognition. And, the processed stylized images are prompted and a selection operation on the stylized images is received to verify an identity of an object executing the selection operation.

Abstract: An aspect can include obtaining, from a device of a user, location data, obtaining, from the device in response to a determination that the location parameter identifies a physical location of a physical environment, a public key of the user, generating, based on the public key and a private key of the user, an NFT linked with the user and the physical environment, determining, in response to a determination that the device satisfies a distance threshold to an entry controller at the physical location, that the NFT and the public key are compatible with a control structure of a smart contract, and transmitting, in response to the determination that that the NFT and the public key are compatible with the control structure of the smart contract, an instruction based on the NFT to modify operation of the entry controller to permit entry to the physical location.

Abstract: A towing assist system for a vehicle includes a marker positioned on a trailer. An imaging device is in connection with the vehicle and configured to capture image data demonstrating a rearward-directed field of view. A controller processes the image data depicting the characteristic marker and detects the characteristic marker in the image data. The controller further identifies a coupler position or coupler height of a coupling interface of the trailer in response to a position of the marker in at least one frame of the image data.

Abstract: A pixel array of an image sensor includes a plurality of color filter array (CFA) cells. Each of the plurality of CFA cells includes first, second, third, and fourth CFA blocks. Each of the first and second CFA blocks includes a plurality of pixels to sense light of a first color. Most pixels of the third CFA block are configured to sense the second color and the third CFA block includes at least one first pixel to sense the first light. Most pixels of the fourth CFA block are configured to sense a third color of light and the fourth CFA block includes at least one second green pixel to sense the first light.

Abstract: A method to operate an analog to digital converter. The method may storing a sampled signal of an input voltage on capacitors, of an up ramp generator and of a down ramp generator to obtain a sampled signal, enabling one of the up ramp generator and the down ramp generator based on a sign of the sampled signal, detecting, on the capacitors, a zero crossing of a stepped ramp that is generated in the one of the up ramp generator and the down ramp generator, and generating a digital representation of the sampled signal based on a number of steps in the stepped ramp.

Abstract: Authentication of electronic document is based on multiple digital signatures incorporated into a blockchain. Structured data, metadata, and instructions may be hashed to generate the multiple digital signatures for distribution via the blockchain. Any peer receiving the blockchain may then verify an authenticity of an electronic document based on any one or more of the multiple digital signatures incorporated into the blockchain.

Abstract: Methods and systems for developing a sizing system through categorization and selection of prototypes, which can be regarded as the most appropriate fit model, is described. Once categorized and prototypes are selected, recommendations for the sizing of a target body part may be issued.

Abstract: In this approach, a system and workflow are provided for generating unique content identifiers (sometimes referred to herein as “Content IDs”) for digital assets. A Content ID is uniquely associated with each piece of content within a customer's asset space The Content ID need not be based on the contents of the asset (such as pixel values of an image), and both perceptual and non-perceptual aspects of identification of the asset may be evaluated to enable different permutations of the same digital asset to have different Content IDs. The system provides for content similarity detection by identifying a content match and surfacing this match within a customer data set, providing automated, scalable, and consistent Content IDs for multiple use cases associated with a digital asset management solution.

Abstract: A method includes receiving seismic training data comprising a plurality of images each including a plurality of traces, predicting a location of a feature in at least some of the plurality of traces based on a location of an amplitude peak therein, applying labels to the locations, classifying pixels of the plurality of images as representing the feature or not representing the feature, using a semantic segmentation model, adjusting the labels based on the classification of the pixels, training, using the adjusted labels and the seismic training data, a machine-learning model to identify the feature, and identifying the feature in a different seismic data set using the trained machine-learning model.

Abstract: Embodiments of document processing systems and methods for intelligent zonal recognition and context mapping are disclosed. These document processing systems and methods may utilize image processing and heuristic techniques to determine key zones from a minimal set of example documents of a document type and map those key zones to a context definition.

Abstract: An image processing device that determines a target subject region to be processed from an image for a specific subject. The device includes at least one processor and at least one memory functioning as a first detection unit configured to detect a first region corresponding to a part having a first feature of the specific subject from the image, a second detection unit configured to detect a second region corresponding to a part having a second feature of the specific subject from the image, an association unit configured to associate the first region detected by the first detection unit and the second region detected by the second detection unit, and a determination unit configured to determine any region of the image including the first region detected by the first detection unit and the second region detected by the second detection unit as the target subject region.

Abstract: An imaging system comprising circuitry configured to obtain (S2) image data of a scene that is illuminated with patterned light (PL), determine (S5, S6) bright regions and dark regions based on the image data, and relate image information related to the bright regions to image information related to the dark regions in order to determine characteristics of atmospheric aerosol particles (AP).

Abstract: An automated checkout system modifies received images of machine-readable labels to improve the performance of a label detection model that the system uses to decode item identifiers encoded in the machine-readable labels. For example, the automated checkout system may transform subregions of an image of a machine-readable label to adjust for distortions in the image's depiction of the machine-readable label. Similarly, the automated checkout system may identify readable regions within received images of machine-readable labels and apply a label detection model to those readable regions. By modifying received images of machine-readable labels, these techniques improve on existing computer-vision technologies by allowing for the effective decoding of machine-readable labels based on real-world images using relatively clean training data.

Abstract: There is a need for more effective and efficient anomalous text detection.

Abstract: In one aspect, an information processing apparatus includes a first acquisition module, a first extraction module, a first generation module, a second extraction module, a derivation module, and a first output control module. The first acquisition module acquires an input image to output a first image and a second image. The first extraction module extracts first characteristic point information from the first image. The first generation module generates a third image obtained by reducing a data amount of the second image. The second extraction module extracts second characteristic point information from the third image. The derivation module derives a difference between the first characteristic point information and the second characteristic point information. The first output control module outputs the third image corrected in accordance with the difference as an output image.

Abstract: In an example, based upon a first image of a face of a first person, a plurality of augmented images may be generated. Based upon the first image and the plurality of augmented images, a first set of facial feature representations may be generated. A second image comprising a representation of a face of a second person may be identified. A second facial feature representation may be generated based upon the second image. It may be determined, based upon the second facial feature representation and the first set of facial feature representations, that the second person is the first person.

Abstract: Objects within an image are assigned a semantic interest that is indicative of their importance to the image as a whole. The objects are detected automatically, and sub-images that span each of the objects are excerpted from the image. An image embedding is determined for each of the sub-images as well as for the whole image by using an image encoder implemented as a trained multi-modal neural network. The degree of similarity between the image embeddings of a sub-image and that of the whole image is used as a measure of the semantic importance of the object portrayed in the sub-image. Objects of high semantic importance comprise the semantic regions of interest of the image. Knowledge of such regions may be used to enhance and improve the efficiency of downstream image-processing tasks, such as image compression, pan and scan, and contrast enhancement.

Abstract: There is provided an image processing apparatus. An obtainment unit obtains a first image, first subject information indicating a first subject detected from the first image, a second image, and second subject information indicating a second subject detected from the second image. A composition unit generates a composite image by compositing the first image and the second image. A recording unit records one of the first subject information and the second subject information in association with the composite image in a case where a similarity between the first subject information and the second subject information satisfies a predetermined criterion, and records both of the first subject information and the second subject information in association with the composite image in a case where the similarity between the first subject information and the second subject information does not satisfy the predetermined criterion.

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: Presented herein are systems and methods for the employment of machine learning models for image processing. A method may include a capture of a video feed including image data of a document at a client device. The client device can provide the video feed to another computing device. The method can include, by the client device or the other computing device object recognition for recognizing a type of document and capturing an image exceeding a quality threshold of the document amongst the frames within the video feed. The method may further include the execution of other image processing operations on the image data to improve the quality of the image or features extracted therefrom. The method may further include anti-fraud detection or scoring operations to determine an amount of risk associated with the image data.

Abstract: A power consumption control device applied to an electronic device includes an image signal processor (ISP), a storage device, a processing circuit, and a control circuit. The ISP is arranged to receive an image signal captured by a camera of the electronic device, and process the image signal to generate a processed image signal. The storage device is arranged to store at least one predetermined image class. The processing circuit is arranged to analyze the processed image signal to detect whether the processed image signal belongs to the at least one predetermined image class to generate a control signal. The control circuit is arranged to switch a mode of the electronic device to a first mode or a second mode according to the control signal, wherein power consumption and performance of the electronic device in the first mode are lower than that in the second mode.

Abstract: Embodiments of the present disclosure relate to a calibration verification method for a camera intrinsic parameter, an apparatus, a device, and a medium. The method includes: acquiring a plurality of reference images photographed by a target camera with a plurality of reference world coordinates under a preset photographing condition, wherein the camera intrinsic parameter of the target camera is calibrated; determining, a first coordinate change parameter corresponding to the plurality of reference world coordinates according to the preset photographing condition, and determining a second coordinate change parameter of the plurality of reference images according to a preset algorithm; determining whether the second coordinate change parameter is consistent with the first coordinate change parameter; and if the second coordinate change parameter is consistent with the first coordinate change parameter, feeding back a verification message indicating successful calibration of the camera intrinsic parameter.

Abstract: A method, computer system, and a computer program product for historical image search is provided. The present invention may include receiving an image search criteria. The present invention may also include generating a composite image search query based on the received image search criteria. The present invention may further include searching for a matching historical image based on the generated composite image search query. The present invention may also include returning a historical image search result.

Abstract: A method for estimating ripeness of produce includes illuminating the produce with light, measuring intensities of the light reflected from the produce at different frequencies, and determining a degree of ripeness of the produce from the relative intensities of the light reflected from the produce at the different frequencies.

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: Provided herein are systems and methods for extracting text from a document. Different optical character recognition (OCR) tools are used to extract different versions of the text in the document. Metrics evaluating the quality of the extracted text are compared to identify and select higher quality extracted text. A selected portion of text is compared to a threshold to ensure minimal quality. The selected portion of text is then saved. Error correction can be applied to the selected portion of text based on errors specific to the OCR tools or the document contents.

Abstract: Technologies are provided herein for adaptively learning and matching modalities of face images. A face image is obtained and a biometric signature is generated of the face image. The biometric signature is compared with a stored biometric signature obtained from data storage. Differences are determined between the biometric signature and the stored biometric signature and compared with a proximity threshold. As a result of the comparison with the proximity threshold, the identity of the person in the face image may be determined or the face image may be stored in data storage in association with the identity of the person.

Abstract: Multimodal techniques are described for classifying start pages and/or document types of an unstructured document image package. To that end, some implementations of the disclosure relate to a method, including: obtaining a document image file including multiple pages and multiple document types; generating, for each page of the multiple pages, using multiple independent trained models, multiple independent predictions, each of the multiple independent predictions indicating: whether or not the page is a first page of a document, or a document type of the multiple document types that the page corresponds to; and generating, for each page of the multiple pages, based on the multiple independent predictions, using a neural network, a final prediction output indicating whether or not the page is the first page of a document, or one of the multiple document types that the page corresponds to.

Abstract: A device receives user interface interaction data that identifies an interaction that a user has with an interface that displays an image of a vehicle. The device generates, by using a data model to process at least a portion of the image, an array of vectors that includes one or more vectors relating to vehicle characteristics of the vehicle. The device assigns one or more weights to the one or more vectors based on the user interface action data. The device determines, based on a similarity analysis, similarity scores that indicate similarities between the array of vectors that include the one or more vectors that have been weighted and other arrays relating to the vehicles depicted in the images. The device selects a subset of the images based on the similarity scores and causes the subset of the images to be displayed.

Abstract: A method of annotating known objects in road images captured from a sensor-equipped vehicle, the method implemented in an annotation system and comprising: receiving at the annotation system a road image containing a view of a known object; receiving ego localization data, as computed in a map frame of reference, via localization applied to sensor data captured by the sensor-equipped vehicle, the ego localization data indicating an image capture pose of the road image in the map frame of reference; determining, from a predetermined road map, an object location of the known object in the map frame of reference, the predetermined road map representing a road layout the map frame of reference, wherein the known object is one of: a piece of road structure, and an object on or adjacent a road; computing, in an image plane defined by the image capture pose, an object projection, by projecting an object model of the known object from the object location into the image plane; and storing, in an image database, image

Abstract: The present disclosure describes systems and techniques for creating a super-resolution image (122) of a scene captured by a user device (102). Natural handheld motion (110) introduces, across multiple frames (204, 206, 208) of an image of a scene, sub-pixel offsets that enable the use of super-resolution computations (210) to form color planes (212, 214, 216), which are accumulated (218) and combined (220) to create a super-resolution image (122) of the scene.

Abstract: A method of identifying a defensive alignment and an offensive alignment in a set-piece is disclosed herein. A computing system receives one or more streams of tracking data. The computing system identifies a set-piece contained in the one or more streams of tracking data. The computing system identifies a defensive alignment of a first team and an offensive alignment of a second team. The computing system extracts, via a convolutional neural network, one or more features corresponding to a type of defensive alignment implemented by the first team by passing the set-piece through the convolutional neural network. The computing system scans the set-piece, via a machine learning algorithm, to identify one or more features indicative of a type of offensive alignment implemented by the second team. The computing system infers the type of defensive alignment implemented by the first team.

Abstract: A method for processing an image includes first obtaining a media image. The media image has a target scene object at least partially shielded. A target shielding object is determined from the media image. The target shielding object at least partially shields the target scene object. Image inpainting is performed on a first region of the media image corresponding to the target shielding object to generate a target media image.

Abstract: A connected component analysis (CCA) method, which can use labels repeatedly, comprising: defining a label pattern comprising a label and a plurality of neighboring labels; setting a center label of a current pixel of a target binary image according to a binary value of the current pixel and the neighboring pixels; setting at least two of the neighboring labels according to whether the current pixel is in any one of a first row, a first column and a last column; and recording the center label to a label buffer. Labels for marking pixels of the target binary image are first center labels, and then are second center labels, and are the first center labels again after the labels are the second center labels.

Abstract: One embodiment provides a method comprising acquiring 3D content comprising a 3D object in 3D space. The 3D object has object information indicative of a location of the 3D object in the 3D space. The method further comprises projecting the 3D object to a 2D object in 2D space based on the object information. The 2D object has one or more 2D vertices indicative of a location of the 2D object in the 2D space. The method further comprises determining one or more latent variables in the 2D space based on the object information and the one or more 2D vertices, and generating a 2D feature database including the one or more latent variables.

Abstract: A processor-implemented method with pose estimation includes: tracking a position of a feature point extracted from image information comprising a plurality of image frames, the image information being received from an image sensor; predicting a current state variable of an estimation model for determining a pose of an electronic device, based on motion information received from a motion sensor; determining noise due to an uncertainty of the estimation model based on a residual between a first position of the feature point extracted from the image frames and a second position of the feature point predicted based on the current state variable; updating the current state variable based on the current state variable, the tracked position of the feature point, and the noise; and determining the pose of the electronic device based on the updated current state variable.

Abstract: A video camera comprises a housing (102) configured of a top housing portion (104), a mid-housing portion (106) and a bottom housing portion (108). The top housing portion is configured as a circular and rounded exterior contoured wall (110) having an exterior recessed feature (112) formed along an edge (114). The mid-housing portion (106) is formed of an IR window ring (116) having an alignment tab (118) extending therefrom, the alignment tab being aligned and recessed within the exterior recessed feature (112) of the rounded exterior contoured wall (110) of the top housing portion (104), and the bottom housing portion (108) providing a camera dome (120) seated within and protruding from the IR window ring (116).

Abstract: An apparatus and method to adjust item recommendations are disclosed herein. A first image attribute of a query image is compared to a second image attribute of each of a plurality of inventory images of a plurality of inventory items to identify the inventory items similar to the query image. Item recommendations comprising the identified inventory items in a first listing order are provided for display at a remote device. A second listing order of the identified inventory items is determined based on a user preference for a particular one of the identified inventory items. At least the second listing order is provided to the remote device for re-display of the item recommendations in accordance with the second listing order.

Abstract: The present system and method relate generally to the field of Robotic Process Automation, particularly to a form data extractor for document processing. The system and method relate to a form extractor for document processing using RPA workflows that can be easily configured for different document types. The form extractor includes a set of templates for identifying the document type (classification) and extracting data from the documents. The templates can be configured, i.e., by the user, by defining the fields to be extracted and the position of the field on the document. The form extractor is resilient to changes in the position of the template on a page, as well as to scan rotation, size, quality, skew angle variations and file formats, thus allowing RPA processes to extract data from documents that need ingestion, independent of how they are created.

Abstract: The invention provides a technique capable of effectively and appropriately removing noise from various kinds of images including noise and artifacts and images in which a noise pattern changes due to a difference in imaging conditions. Based on a noise removal technique using AI, noise characteristics including artifacts are analyzed for each image, the image is classified based on an analysis result, an optimal neural network for a noise processing is applied for each classification, and the noise and the artifacts are reduced.

Abstract: The disclosure relates to AI-based machine-learning and natural language modeling to identify semantic similarities between sets of content having natural language text. For example, a system may generate a relevance classification that indicates whether content such as articles are non-specifically relevant to charities without identifying a particular charity. If the content is non-specifically relevant to charities, the system may apply a natural language model to generate sentence embeddings based on the content and determine a level similarity between the sentence embeddings and a query embedding generated from a charity query. The charity query may itself be generated from a full description of the charity through an encoder-decoder architecture with reinforcement learning.

Abstract: Systems, methods, and data storage devices for image grouping in an end user device using trained machine learning group classifiers are described. The end user device may include an image group classifier configured to classify new image data objects using an image classification algorithm and set of machine learning parameters previously trained for a specific image group. The end user device may determine embeddings that quantify features of the target image object and use those embeddings and the image group classifier to selectively associate group identifiers with each new image data object received or generated by the end user device. Calibration, including selection and training, of the image group classifiers and ranking of classified images are also described.

Abstract: A game image generation unit 112 generates a moving image of content. A receiving unit 104 receives a displayed image changing request. Upon reception of the changing request by the receiving unit 104, a display control unit 106 acquires information regarding a frame image of the content from the frame buffer 108. A system image generation unit 120 uses the information regarding the frame image to generate an image that differs from the frame image. The display control unit 106 acquires information regarding an end frame image of the content or an image preceding the end frame image by a predetermined number of frames.

Abstract: An image differentiation system receives input feature vectors for multiple input images and reference feature vectors for multiple reference images. In some cases, the feature vectors are extracted by an image feature extraction module trained based on training image triplets. A differentiability scoring module determines a differentiability score for each input image based on a distance between the input feature vectors and the reference feature vectors. The distance for each reference feature vector is modified by a weighting factor based on interaction metrics associated with the corresponding reference image. In some cases, an input image is identified as a differentiated image based on the corresponding differentiability score. Additionally or alternatively, an image modification module determines an image modification that increases the differentiability score of the input image. The image modification module generates a recommended image by applying the image modification to the input image.

Abstract: A method includes receiving 2D image data corresponding to a 2D image of a human face of a subject. The method further includes determining a textual identifier that describes a facial feature of the human face represented by the 2D image. The method further includes providing, to a first generative machine learning model, a first prompt including information identifying the textual identifier that describes the facial feature of the human face. The method further includes obtaining, from the first generative machine learning model, a first output identifying, among a plurality of sets of false eyelashes, a set of false eyelashes selected to suit the human face of the subject based on the facial feature.