Abstract: In one aspect, an example method to be performed by a computing device includes (a) receiving a request to use a camera of the computing device; (b) in response to receiving the request, (i) using a microphone of the computing device to capture audio content and (ii) using the camera of the computing device to capture an image; (c) identifying reference audio content that has at least a threshold extent of similarity with the captured audio content; and (d) outputting an indication of the identified reference audio content while displaying the captured image.

Abstract: Provided are a video special effect configuration file generation method and apparatus, and a video rendering method and apparatus. The video special effect configuration file generation method includes: obtaining a reference image; receiving a screen splitting processing operation of a user on the reference image; performing screen splitting processing on the reference image based on the screen splitting processing operation to obtain a plurality of sub-screens; and associating, in response to a special effect setting operation of the user on a target sub-screen among the plurality of sub-screens, at least one first special effect corresponding to the special effect setting operation with the target sub-screen, to generate a video special effect configuration file. The user can customize the screen splitting processing manner and the rendering special effect of the sub-screen, the video special effect configuration file generation method is more flexible and is more convenient for use.

Abstract: Techniques are generally described for generation of synthetic image data. In some examples, a selection of a first image may be received. The first image may depict at least a first object having a plurality of image attributes representing visual characteristics of the at least the first object. In some examples, a selection of a first image attribute of the plurality of image attributes to be maintained in subsequently-generated images may be received. In various examples, a first machine learning model may generate a second image having the plurality of image attributes. The change in an appearance of the first image attribute may be minimized in the second image while a change in the appearance of other attributes of the plurality of image attributes may be maximized in the second image.

Abstract: Provided is a method, device, apparatus for controlling a display picture of a mobile terminal, and a storage medium. The mobile terminal includes a touch screen and a touch panel. The first touch operation imposed on the first preset area of the touch screen and the second touch operation imposed on the second preset area of the touch panel are determined, and whether the first touch operation and the second touch operation meet the preset zoom condition is determined, and if so, the zoom control is performed on the display picture in the third preset area of the touch screen.

Abstract: Machine-readable storage media having instructions stored therein that, when executed by a processor of a mobile device, configure the mobile device to capture a check image for funds to be deposited into a recipient account. The mobile device configured to display a request to a user of the mobile device to provide one or more portions of a MICR line for the received check image and receive user inputs from the user specifying the one or more portions of the MICR line. The mobile device configured to transmit a message to a bank account computer system associated with the recipient account, the message including data specifying the one or more portions of the MICR line.

Abstract: An image processing apparatus according to an aspect of the present disclosure includes an optical character recognition (OCR) unit configured to sequentially execute processing related to OCR on image data on a plurality of documents, a generation unit configured to select one of the plurality of documents subjected to the processing related to OCR, and to generate a recommendation content about an index to be assigned to the one selected document based on an index extraction rule, and a confirmation unit configured to present the generated recommendation content to a user and to assign an index to the one document based on an instruction from the user. The processing to be executed by the OCR unit and processing to be executed by the confirmation unit are executed in parallel.

Abstract: Systems and methods for services for assisting programming are disclosed. The systems and methods can be used to, during edit time, for program code or data of interest, identify one or more services available to the program code or the data of interest, generating a context for the one or more services, execute code for the one or more services within the context to generate a result for each of the one or more services, analyze the result for each of the one or more services to select a subset of results based on criteria associated with the program code, the data of interest, or the one or more services, and offer, to a user, services corresponding to the subset of results or the subset of results as suggestions to facilitate further development of the program code or use of the data of interest.

Abstract: A method of detecting an object depicted in a digital image includes: detecting a plurality of identifying features of the object, wherein the plurality of identifying features are located internally with respect to the object; projecting a location of region(s) of interest of the object based on the plurality of identifying features, where each region of interest depicts content; building and/or selecting an extraction model configured to extract the content based at least in part on: the location of the region(s) of interest, the of identifying feature(s), or both; and extracting the some or all of the content from the digital image using the extraction model. Corresponding system and computer program product embodiments are disclosed. The inventive concepts enable reliable extraction of data from digital images where portions of an object are obscured/missing, and/or depicted on a complex background.

Abstract: A system for format-agnostic document ingestion including a document ingestion server and a database is disclosed. The server is configured to receive an image of a document comprising text in an unknown format, convert the image, using OCR, into a plurality of text elements a content, a size, and an absolute position. The server is also configured to retrieve data detectors from the database, each associated with a data type anticipated to be in the document, and comprising at least one identifier and direction, and at least one validation criteria. The server is also configured to identify a potential descriptor by comparing the content of each text element with the at least one identifier, and then determine if the text element pointed to by the data detector meets the validation criteria. Finally, the server is configured to associate the validated text element with the data detector, and store the content.

Abstract: Aspects of the disclosure provide for mechanisms for identification of objects in images using neural networks. A method of the disclosure includes: obtaining an image, representing each element of a plurality of elements of the image via an input vector of a plurality of input vectors, each input vector having one or more parameters pertaining to visual appearance of a respective element of the image, providing the plurality of input vectors to a first subnetwork of a neural network to obtain a plurality of output vectors, wherein each of the plurality of output vectors is associated with an element of the image, identifying, based on the plurality of output vectors, a sub-plurality of elements of the image as belonging to the image of the object, and determining, based on locations of the sub-plurality of elements, a location of an image of an object within the image.

Abstract: A biological pattern information processing device includes: a biological pattern information acquisition unit that acquires biological pattern information indicating a biological pattern; and a singular region detection unit that detects a singular region including damage, from the biological pattern indicated by the acquired biological pattern information.

Abstract: The relay server may receive a first service request from a communication device and send, in a case where the first service request, is received from the communication device, a sending instruction to the communication device. The sending instruction may be for instructing to send first target data to a first service providing server. In a case where the communication device receives the sending instruction from the relay server, the communication device may send the first target data to the first service providing server without an intervention of the relay server. The relay server may receive a second service request from the communication device and send, in a case where the second service request is received from the communication device, the second target data received from the communication device to the second service providing server.

Abstract: Techniques are disclosed for sharing user markings between digital documents and corresponding physically printed documents. The sharing is facilitated using an Augmented Reality (AR) device, such as a smartphone or a tablet. The device streams images of a page of a book on a display. The device accesses a corresponding digital document that is a digital version of content printed on the book. In an example, the digital document has a digital user marking, e.g., a comment associated with a paragraph of the digital document, wherein a corresponding paragraph of the physical book lacks any such comment. When the device streams the images of the page of the book on the display, the device appends the digital comment on the paragraph of the page of the book within the image stream. Thus, the user can view the digital comment in the AR environment, while reading the physical book.

Abstract: Method for creating by a user of a social media content represented as a message to be viewed in Augmented Reality. The invention presents a method of creation of social media content in association with a real-world object. With the use of this method, such social media content can be created by user, who is in proximity of a real-world object with which user wishes to associate with (add to) social media content, using a mobile device. The social media content thus created can be viewed by same user or other social media users by pointing a mobile device camera on the real-world object with which the social media content was associated with (added to). This is being achieved by implementing specific algorithm that uses Artificial Neural Network(s) for instant remembering, or identifying, visually distinctive real-world objects that had a social media content associated with (added to) it.

Abstract: An apparatus, a method, and a computer program product are provided. The apparatus detects an eye gaze on a first region in a real world scene, sets a boundary that surrounds the first region, the boundary excluding at least a second region in the real world scene, performs an object recognition procedure on the first region within the boundary, and refrains from performing an object recognition procedure on the at least the second region.

Abstract: An image processing system which corrects a text obtained by optical character recognition (OCR) using a neural network which has performed learning based on a falsely recognized portion of OCR and a text near the falsely recognized portion is provided. The image processing system acquires a neural network model which has been trained based on learning data in which first text information included in print data and second text information acquired by performing optical character recognition (OCR) processing on an image that is based on the print data are associated with each other, acquires an image obtained by a scanner, acquires third text information which is generated by performing OCR processing on the image obtained by the scanner, and outputs fourth text information according to inputting of the third text information based on the neural network model.

Abstract: An information processing apparatus includes a receiving unit and a controller. The receiving unit receives an extraction-area image indicating an extraction area. The extraction area includes a fill-in area in which a writer handwrites information. When an instruction to correct a recognition result for the information written in the fill-in area indicated by the extraction-area image is given, the controller causes a display unit to display a different extraction-area image similar to the extraction-area image.

Abstract: An image forming apparatus includes: a transceiver circuit configured to transmit a signal. A carriage having a recording head is movable relative to the transceiver circuit. A counter counts how many times the carriage moves. An amplifier circuit mounted on the carriage receives the signal from the transceiver circuit through a cable and amplifies the received signal. A carriage controller changes a gain of the amplifier circuit, based on a count value of the counter.

Abstract: An information processing apparatus includes a character recognition section that performs character recognition of an input image to output a character recognition result, a receiving section that receives an input of a character recognition result by a person on the input image, a detection section that detects a strikethrough from the input image, a matching section that matches the character recognition result output by the character recognition section with the character recognition result by the person, which is received by the receiving section, and a control section that performs control for causing the matching section to perform matching so as to obtain a final character recognition result based on a result of the matching, in a case where the detection section detects the strikethrough.

Abstract: A storage medium, and a method and system for simulating photography in a virtual reality scene. The method comprises: firstly, in a virtual reality scene, adjusting composition parameters of a current viewport to obtain initial image data; then, adjusting camera parameters of the initial image data to obtain modified image data; and finally carrying out anti-distortion processing on the modified image data to output a target image. The demands of users for personalizing a 360-degree panoramic photo and outputting satisfying target images are satisfied. The method is not only simple to be operated, but also conducive to the further promotion and application of virtual reality technology.

Abstract: A correction history recording unit that records region information of a correction site with respect to text data converted from an original image as correction history information, an accuracy calculation unit that calculates accuracy of optical character recognition for each of individual regions on a layout of the original image on the basis of the correction history information, a distribution image generation unit and a distribution image display unit which generate and display a distribution image in which a difference in magnitude of accuracy is shown as a difference in a display aspect for every individual region are included so as to generate and display the distribution image that is distinguished for every individual region by reflecting a tendency in which a character recognition rate in a certain region on a layout of the original image may decrease due to various cases including a format of an original document, a state of an OCR device, and the like.

Abstract: Machine-readable storage media having instructions stored therein that, when executed by a processor of a mobile device, configure the mobile device to capture a check image for funds to be deposited into a recipient account. The mobile device configured to display a request to a user of the mobile device to provide one or more portions of a MICR line for the received check image and receive user inputs from the user specifying the one or more portions of the MICR line. The mobile device configured to transmit a message to a bank account computer system associated with the recipient account, the message including data specifying the one or more portions of the MICR line.

Abstract: Techniques are disclosed for performing optical character recognition (OCR) by assessing and improving quality of electronic documents to perform the OCR. For example a method for identifying information in an electronic document includes obtaining a reference image of the electronic document, distorting the reference image by adjusting different sets of one or more parameters associated with a quality of the reference image to generate a plurality of distorted images, analyzing each distorted image to detect the adjusted set of parameters and corresponding adjusted values, determining an accuracy of detection of the set of parameters and the adjusted values, and training a model based at least on the plurality of distorted images and the accuracy of the detection, wherein the trained model determines at least a first technique for adjusting a set of parameters in a second image to prepare the second image for optical character recognition.

Abstract: A technique provides mobile device security to a mobile device. The technique involves, in response to operation of a camera of the mobile device, receiving image data from the camera, the image data representing a visual image captured by the camera. The technique further involves performing an image evaluation operation which electronically analyzes the image data received from the camera to determine whether the image data contains sensitive information. The technique further involves, based on a result of the image evaluation operation, performing a security operation that provides security to the mobile device.

Abstract: A method for a user to paint an image includes generating a display of a room image uploaded by the user. The method also includes employing a straight-line masking tool to block off a first area of the room image with a straight line such that color will not be applied to the first area when color is applied to a second area of the room image. The method also includes employing a polygon masking tool to draw at least three lines to mask off a selected polygon area of the room image such that color can be applied by the user to an inside of the selected polygon area when the user selects the inside of the selected polygon area and an outside of the selected polygon area when the user selects the outside of the selected polygon area.

Abstract: The AUTOMATIC REMOTE DEPOSIT IMAGE PREPARATION APPARATUSES, METHODS AND SYSTEMS (hereinafter “MultiCrop”) transforms uploaded check images and check deposit information inputs via MultiCrop components image into deposit confirmation outputs. For example, in one embodiment, a user may employ a personal computer connected to a web camera, and/or a smartphone with a built-in camera to initiate the remote deposit by holding a check in front of the camera, and the MultiCrop may capture images of the check and send them to a financial institution for deposit processing.

Abstract: Embodiments include methods, systems, and computer program products method for obstruction free smartwatch interactions. The computer-implemented method includes pairing, using a processor, a smartwatch, and a companion device. The processor detects one or more obstructions to a display area of the smartwatch. The processor further determines that the one or more obstructions are caused by a user attempting to interact with the smartwatch. The method further projects content associated with the smartwatch onto a surface by the companion device in response to the one or more obstructions being caused by the user attempting to interact with the smartwatch. The method further receives a first input at the smartwatch via an interaction with the projected content associated with the smartwatch.

Abstract: A controller for a printer, a printing system, method for controlling a printer and a software medium are disclosed. The controller includes a process monitor configured to determine which images of a plurality of images are currently being processed simultaneously by the printer; and a display configured to indicate to a user, based on the determining by the process monitor, which images of the plurality of images are currently being processed simultaneously by the printer.

Abstract: A photoelectric conversion device having plural photoelectric conversion pixels includes an imaging unit, a position identifying unit, an interpolation determining unit, and an interpolation processing unit. The imaging unit generates image data for each of plural colors based on light received in the photoelectric conversion pixels. The position identifying unit detects in the photoelectric conversion pixels a defective pixel outputting an electrical signal at an abnormal level, and stores position information of the defective pixel. The interpolation deter mining unit determines, based on respective pixel values of peripheral pixels peripheral to the defective pixel, whether to perform an interpolation process on the defective pixel. The interpolation processing unit performs the interpolation process on the defective pixel when the interpolation determining unit determines to perform the interpolation process on the defective pixel.

Abstract: Techniques for error correction using a history list comprising at least one misrecognition and correction information associated with each of the at least one misrecognitions indicating how a user corrected the associated misrecognition. The techniques include converting data input from a user to generate a text segment, determining whether at least a portion of the text segment appears in the history list as one of the at least one misrecognitions, if the at least a portion of the text segment appears in the history list as one of the at least one misrecognitions, obtaining the correction information associated with the at least one misrecognition, and correcting the at least a portion of the text segment based, at least in part, on the correction information.

Abstract: A method of presenting computer-generated search result information can include receiving a search request from a client computer; identifying a plurality of search results responsive to the search request; ranking the plurality of search results using content in one or more web notebooks; and providing the ranked plurality of search results for presentation in the client computer. Using the content can include determining whether at least one of a title, a heading, clipped content, metadata or a user-annotation in at least one web notebook relates to the search request and, if so, increasing a ranking of at least one search result referenced by the at least one web notebook.

Abstract: In the disclosed systems and methods for competitive scene completion, a user selects from among one or more affordances, each representing a different challenge and comprising a scene image and plurality of markers. Each marker has independent scene coordinates and a type. The scene and markers of the selected challenge is displayed. For each user marker selection, corresponding furnishing units are displayed. The units match the marker type and include units retained and not retained by the user. User unit selection results in display of a graphic of the selected unit at the corresponding coordinates within the scene. The scene is thereby populated with graphics. The unit selections are submitted upon satisfaction of a challenge completion criterion specifying which scene coordinates must be populated. Responsive to submission, the user unit selections are subjected to community vote on a remote server and the results are provided to the user.

Abstract: A framework is provided for associating dense images with topics. The framework is trained utilizing images, each having multiple regions, multiple visual characteristics and multiple keyword tags associated therewith. For each region of each image, visual features are computed from the visual characteristics utilizing a convolutional neural network, and an image feature vector is generated from the visual features. The keyword tags are utilized to generate a weighted word vector for each image by calculating a weighted average of word vector representations representing keyword tags associated with the image. The image feature vector and the weighted word vector are aligned in a common embedding space and a heat map is computed for the image. Once trained, the framework can be utilized to automatically tag images and rank the relevance of images with respect to queried keywords based upon associated heat maps.

Abstract: Techniques are described for facilitating performance of tasks involving human review of media data (e.g., images, audio clips, video clips, etc.), such as to identify one or more targets of interest. The media data review may be performed for various reasons, such as to assist in locating one or more target objects in a large geographical area (e.g., one or more missing people or vehicles) based on human review of large quantities of images that each correspond to a small subset of the geographical area. When one or more of the reviewed media data pieces are identified as being relevant, information about those identified media data pieces may be used in various ways. Furthermore, in at least some situations, the media data review may be part of a charitable effort that uses human volunteers to review the media data without monetary payment or other compensation.

Abstract: An image of a check may be presented for payment in a banking system in place of the physical paper check. The check to be deposited can be collected from a depositor using a scanner. A web site, accessed through a depositor's web browser, can be used to drive the process of collecting the check, but in some contexts (e.g., in less popular computing environments, such as those that do not run the most popular operating systems), it is economically infeasible to obtain the certificates that would be used to allow a program executing in the web browser to control the scanner. Thus, a depositor can be instructed to capture and upload images of the check in the form of files, where the image files are then presented for payment through a banking system.

Abstract: Machine-readable storage media having instructions stored therein that, when executed by a processor of a mobile device, configure the mobile device to capture a check image for funds to be deposited into a recipient account. The mobile device configured to display a request to a user of the mobile device to provide one or more portions of a MICR line for the received check image and receive user inputs from the user specifying the one or more portions of the MICR line. The mobile device configured to transmit a message to a bank account computer system associated with the recipient account, the message including data specifying the one or more portions of the MICR line.

Abstract: A multifunction peripheral includes an answerer identifying unit, a character data extracting unit, a correct/incorrect determining unit, a question data extracting unit, a question sheet image data creating unit, and an image formation control unit. The correct/incorrect determining unit determines answers on a question sheet as correct or incorrect based on characters extracted by the character data extracting unit. The question data extracting unit extracts a plurality of questions from question data stored in a storage unit in accordance with the ratio of correct answers determined by the correct/incorrect determining unit, for each of answerers identified by the answerer identifying unit. The question sheet image data creating unit creates image data of the question sheet with the questions, which are extracted from the question data by the question data extracting unit, arranged thereon.

Abstract: Embodiments of methods to designate alternates of assets, methods to display representations of alternates, user interfaces, computer products, and digital assets are generally described herein. Other embodiments may be described and claimed.

Abstract: Techniques are described for facilitating performance of tasks supplied by task requesters, such as by a task exchange server interacting with mobile task performer users available to perform tasks at various geographical locations. Some or all of the tasks may each be associated with geographical locations and/or other device-related criteria related to the performance of the task, and one or more mobile task performer users may be identified as being appropriate to perform the task based on the location of, qualifications of, and/or characteristics of mobile device(s) of the user. Such identified task performer users may then be notified of such appropriate tasks in various ways, such as by sending one or more electronic messages with information about the tasks to one or more mobile devices of the users, and may in some situations use one or more of their mobile devices as part of the task performance.

Abstract: A recommendation system can be configured to customize search results and/or recommendations of content (e.g., customized products, products, advertising, layouts, etc.) using online and/or offline activity captured on a user population. The system can be configured to customize the content returned to users to achieve specific behaviors and/or influence the current user's behavior, responsive to modeling previous users. For example, the system can capture and aggregate user behavior/activity and score content based on the actions taken with respect to the content. In some examples, the scoring can be filtered or augmented by matching current user characteristics to characteristics of the previous users. The scoring can be generated independent of the language in which the activity/user behavior occurred. According to one embodiment, the system is configured to generate language independent models and utilize the language independent modeling to deliver customized content (e.g.

Abstract: Techniques are described for facilitating interactions between task requesters who have tasks that are available to be performed and task performers who are available to perform tasks, such as by an intermediary electronic marketplace or other task fulfillment facilitator system. In some situations, support is provided in various ways for using multiple human languages when supplying and performing tasks. For example, some tasks may have associated languages, and some tasks may further have multiple task variants that each have a distinct associated language. A user may then request information about tasks in a particular language, and receive information about tasks and/or task variants associated with that language. Furthermore, some tasks and task variants may further be associated with locales that include particular languages and/or various other factors, including geographical areas, and such locales may similarly be used to identify appropriate corresponding users that match the various locale factors.

Abstract: There is provided a personal information collection system comprising: an image reading unit configured to read an image of a document including personal information; an image dividing unit configured to divide a part of the image of the document corresponding to the personal information into a plurality of divided images; a correspondence management unit configured to manage correspondence relation between the divided images and an original image that is the part of the image of the document before being divided; a data entry unit configured to accept data input based on a visual observation of the divided images; and a connection unit configured to connect the input data based on the correspondence relation.

Abstract: Techniques are described for facilitating performance of tasks by human users. A task exchange server system acts an intermediary to facilitate performance by human task performer users of tasks provided by other task requesters, such as by providing information about tasks via an electronically accessible site. The task exchange server may further cause information about tasks to be provided to at least some users as they interact with third-party sites not provided by the task exchange server, such as third-party sites operated by entities unrelated to the task exchange server's operator. The third-party sites may include information about tasks along with other information that the third-party sites provide to users, or instead a separate client-side program executing on computing devices of certain users may obtain and present information about tasks to the users, such as in conjunction with information provided by unaffiliated third-party sites.

Abstract: A data verification system is configured to verify machine-recognized data elements acquired during a machine-implemented data acquisition process. The system includes a data verification workstation, an image server, and a data entry server. The data verification workstation is configured to obtain document images from the image server, present portions of document images to an operator, wherein the document images include text, and receive input from the operator based on the text. The input includes data elements. The data verification workstation is also configured to acquire machine-recognized data elements from the data entry server. The machine-recognized data elements were acquired from the document image during a machine-implemented data acquisition process based on the text.

Abstract: Machine-readable storage media having instructions stored therein that, when executed by a processor of a mobile device, configure the mobile device to capture a check image for funds to be deposited into a recipient account. The mobile device configured to display a request to a user of the mobile device to provide one or more portions of a MICR line for the received check image and receive user inputs from the user specifying the one or more portions of the MICR line. The mobile device configured to transmit a message to a bank account computer system associated with the recipient account, the message including data specifying the one or more portions of the MICR line.

Abstract: A system and method for implementing an efficient and easy to user interface for a touch screen device. A cursor may be placed by a user using simple inputs. The device operates places the cursor coarsely and refines the cursor placement upon further input from the user. Text may be selected using a gripper associated with the cursor. The user interface allows text selection without occluding the text being selected with the user's finger or the gripper. For selecting text in a multi-line block of text, a dynamic safety zone is implemented to simplify text selection for the user.

Abstract: Various embodiments enable a device to perform tasks such as processing an image to recognize and locate text in the image, and providing the recognized text an application executing on the device for performing a function (e.g., calling a number, opening an internet browser, etc.) associated with the recognized text. In at least one embodiment, processing the image includes substantially simultaneously or concurrently processing the image with at least two recognition engines, such as at least two optical character recognition (OCR) engines, running in a multithreaded mode. In at least one embodiment, the recognition engines can be tuned so that their respective processing speeds are roughly the same. Utilizing multiple recognition engines enables processing latency to be close to that of using only one recognition engine.

Abstract: Methods and systems receive an image-processing request relating to user images from a user. Such methods and systems classify the user images into user-request image-element categories. Such methods and systems also retrieve previously stored user-specific preferences for the user-request image-element categories from a computer storage, when the previously stored user-specific preferences for the user-request image-element categories are maintained in the computer storage. However, when the previously stored user-specific preferences for the user-request image-element categories are not maintained in (are absent from) the computer storage, such methods and systems obtain additional user-specific preferences for the user-request image-element categories. Such methods and systems can then processes the image-processing request by altering renditions of the user images according to the previously stored user-specific preferences and/or the additional user-specific preferences.

Abstract: Functionality is described herein by which plural environment-sensing applications capture information from an environment in a fine-grained and least-privileged manner. By doing so, the functionality reduces the risk that private information that appears within the environment will be released to unauthorized parties. Among other aspects, the functionality provides an error correction mechanism for reducing the incidence of false positives in the detection of objects, an offloading technique for delegating computationally intensive recognition tasks to a remote computing framework, and a visualization module by which a user may inspect the access rights to be granted (or already granted) to each application.

Abstract: A non-transitory machine readable medium that has a computer program for adjusting color values of an image represented in a color space. The image includes several pixels. Each pixel includes a set of color values. The computer program receives a selection of a location on the image. The computer program determines a type of content that is associated with the selected location on the image. From several different image editing operations, the computer program selects a set of image editing operations based on the determined type of content. The computer program displays a set of user interface controls that is associated with the selected set of image editing operations.