Abstract: The image forming apparatus includes a sheet conveyance part, an image forming part, and a sheet reading unit. The sheet reading unit includes a line sensor. The line sensor includes split line sensors. The line sensor reads a conveyed sheet. The line sensor includes a plurality of split line sensors. The split line sensors are placed at non-stretching positions, respectively. Each non-stretching position is such a position that as in the main scanning direction, a main-scanning-direction distance from a gap between one split line sensor and another split line sensor to an ideal edge position of every usable regular size exceeds a permissible value.

Abstract: A machine may be configured to execute a machine-learning process for identifying and understanding fine properties of various items of various types by using images and associated corresponding annotations, such as titles, captions, tags, keywords, or other textual information applied to these images. By use of a machine-learning process, the machine may perform property identification accurately and without human intervention. These item properties may be used as annotations for other images that have similar features. Accordingly, the machine may answer user-submitted questions, such as “What do rustic items look like?,” and items or images depicting items that are deemed to be rustic can be readily identified, classified, ranked, or any suitable combination thereof.

Abstract: A method for data-centric networked application development includes: modifying a graphical user interface of a networked application development environment with a selectable component for including a reusable data entity in a project, the reusable data entity being defined and bound to a form component via interaction with the graphical user interface; and configuring a block of a data-centric form of the project with the form component in response to selection of the selectable component at a design surface of the graphical user interface.

Abstract: Embodiments are disclosed for determining a context-aware text color recommendation for text at a text location on an image. In particular, in one or more embodiments, the disclosed systems and methods comprise obtaining an image and a text location on the image, identifying at least one color theme based on a color harmonic template associated with the image, modifying the at least one color theme based on characteristics of the image, determining accessibility for at least one color in the at least one color theme based on the text location on the image, and determining a color palette recommendation for text at the text location on the image based on the determined accessibility for the at least one color in the at least one color theme.

Abstract: Co-browsing allows a providing party to access visual content on a computing device for sharing with one or more other parties. The parties receiving the shared image may have dissimilar security authorizations. Accordingly, systems and methods are provided that enable shared content, such as a document, web page viewed in a browser, etc., to automatically be redacted to block those parties who are not authorized to view the content. For example, a neural network may be utilized to scan the document and provide specific redacted copies to the parties so each can view the image of the content with unauthorized content redacted.

Abstract: Audio based transactions are getting more popular and are envisaged to become common in years to come. With the rise in data protection regulations, muting portions of the audio files is necessary to hide sensitive information from an eavesdropper or accidental hearing by an entity who gets unauthorized access to these audio files. However, it is realized that deleted transaction information in a muted audio files make audit of the transaction challenging and impossible. Embodiments of the present disclosure provide systems and methods of muting audio information in multimedia files and retrieval thereof which is masked and further allows for reconstruction of the original audio conversation or restoration Private to an Entity (P2aE) information without original audio reconstruction when auditing is being exercised.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for obtaining, in real-time from an image capture device, a video stream comprising images of a document by a computing device. The computing device provides, for display in an image preview window, the video stream overlaid with a graphical capture guide. In response to detecting a lighting artifact in at least one image of the video stream, the computing device modifies the graphical capture guide within the image preview window. The computing device captures one or more of the images of the document from the video stream.

Abstract: A computer-implemented technique is described herein for using a machine-trained model to identify individual objects within images. The technique then creates a relational index for the identified objects. That is, each index entry in the relational index is associated with a given object, and includes a set of attributes pertaining to the given object. One such attribute identifies at least one latent semantic vector associated with the given object. Each attribute provides a way of linking the given object to one or more other objects in the relational index. In one application of this technique, a user may submit a query that specifies a query object. The technique consults the relational index to find one or more objects that are related to the query object. In some cases, the query object and each of the other objects have a complementary relationship.

Abstract: Techniques for encapsulating video streams containing multiple coded views in a media file are described herein. In one example, a method includes parsing a track of multiview video data, wherein the track includes at least one depth view. The method further includes parsing information to determine a spatial resolution associated with the depth view, wherein decoding the spatial resolution does not require parsing of a sequence parameter set of the depth view. Another example method includes composing a track of multiview video data, wherein the track includes the one or more views. The example method further includes composing information to indicate a spatial resolution associated with the depth view, wherein decoding the spatial resolution does not require parsing of a sequence parameter set of the depth view.

Abstract: Cloud-based methods and systems for content sharing are disclosed. In some embodiments, the systems may include one or more processors configured to: receive, from a client device, an instruction for sharing a designated digital asset; retrieve the designated digital asset from a storage device; determine provenance of the designated digital asset based on metadata of the designated digital asset; generate authentication information based on the provenance of the designated digital asset; identify sensitive information in the designated digital asset; generate a redacted version of the designated digital asset by modifying content of the designated digital asset to alter the identified sensitive information; and provide the redacted version and authentication information of the designated digital asset to a recipient of the designated digital asset.

Abstract: Disclosed is a method of acquiring an image of a target to provide an output video image that has a plurality of frame images. The method includes the steps of receiving a series of frame images from a video camera, using a processor to manipulate the series of frame images from a video camera, using a processor to manipulate the series of frame images, which includes determining a reference resolution for providing output frame images, and displaying and/or storing the manipulated series of frame images as the output video image without changing a resolution of the output frame images. Also disclosed is a document imaging apparatus that includes a digital imaging unit. The digital imaging unit contains optics that having an infinite focal length. The document imaging apparatus also includes a processor that is coupled to the digital imaging unit and that is configured to cause the digital imaging unit to zoom in or zoom out in real-time while maintaining a resolution value of stored images constant.

Abstract: At least one processor in a content distribution device in a multichannel video program distributor (MVPD) system receives a video feed, a plurality of triggers, and metadata from a broadcast provider system via a communication network, and determines a plurality of segments in the received video feed. The plurality of segments are determined based on the received plurality of triggers and the metadata. The processor embeds at least one content marker in at least one segment of the plurality of segments. The at least one content marker includes attribute information associated with at least one video-on-demand (VOD) content asset. The processor dynamically generates the at least one VOD content asset based on the at least one content marker, and transmits the at least one VOD content asset to at least one server communicatively coupled with the MVPD system.

Abstract: A remote surveillance apparatus and method comprising a camera movably coupled to a mast and configured to capture video data and transmit the captured video data, a router configured to receive the captured video data and wirelessly retransmit the captured video data, via a modem, to a user computing device in response to a request from the user computing device, and an enclosure coupled to the mast and housing the router and the modem.

Abstract: A marker for occluding a foreign matter in an acquired image contains a mark part whose surface is provided with a two-side continuous pattern formed by combining at least one or multiple primitives; and a fixing part which fixes a marker to a surface of foreign matter in the acquired image with the mark part to facilitate algorithm recognition and marking. The method for recognizing a foreign matter marker in an image includes the steps of performing edge detection on a planar image to acquire an edge map in the planar image; and extracting all contours in the edge map. A certain number of alternative straight-line segments are determined using an algorithm; a region is determined according to the position of each alternative straight-line segment; and finally the region of the approximate area above or below the marker is used.

Abstract: Techniques for encapsulating video streams containing multiple coded views in a media file are described herein. In one example, a method includes parsing a track of multiview video data, wherein the track includes at least one depth view. The method further includes parsing information to determine a spatial resolution associated with the depth view, wherein decoding the spatial resolution does not require parsing of a sequence parameter set of the depth view. Another example method includes composing a track of multiview video data, wherein the track includes the one or more views. The example method further includes composing information to indicate a spatial resolution associated with the depth view, wherein decoding the spatial resolution does not require parsing of a sequence parameter set of the depth view.

Abstract: An image-processing apparatus and method for quantization partitioning for enhanced image compression, includes storage of an input image in a first storage space having a first storage access bandwidth. The image-processing apparatus selects a plurality of QP values from a defined QP range for a first block of a plurality of blocks of the input image. The plurality of QP values are selected from the defined QP range based on defined criteria. The image-processing apparatus is configured to encode, by the selected plurality of QP values, the first block to generate an encoded bit stream of the first block. The encoded bit stream of the first block is storable in a reduced second storage space in the memory with a reduced second storage access bandwidth.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for obtaining, in real-time from an image capture device, a video stream comprising images of a document by a computing device. The computing device provides, for display in an image preview window, the video stream overlaid with a graphical capture guide. In response to detecting a lighting artifact in at least one image of the video stream, the computing device modifies the graphical capture guide within the image preview window. The computing device captures one or more of the images of the document from the video stream.

Abstract: A system for document processing including decomposing an image of a document into at least one data entry region sub-image, providing the data entry region sub-image to a data entry clerk available for processing the data entry region sub-image, receiving from the data entry clerk a data entry value associated with the data entry region sub-image, and validating the data entry value.

Abstract: A method, system, and apparatus are provided for processing tables embedded within documents wherein a first table header is detected by using semantic groupings of table header terms to identify a minimum number of table header terms in a scanned line of an text document; a potential data zone is extracted by applying white space correlation analysis to a portion of the text document that is adjacent to the first table header; one or more data zone columns from the potential data zone are grouped and aligned with a corresponding header column in the first table header to form a candidate table; data cleansing is performed on the candidate table; and then one or more columns of the candidate table are evaluated using natural language processing to apply a specified table analysis.

Abstract: A clipping processor is configured to estimate a background pixel value which is a read value of a background board and to clip an image of an original document from a read image based on the background pixel value which is estimated, the read value changing due to an increase in distance between a sensor and the background board caused by the original document, the read image being a result of reading an area including the original document and the background board.

Abstract: This disclosure relates to training a classifier algorithm that can be used for automatically selecting tags to be applied to a received image. For example, a computing device can group training images together based on the training images having similar tags. The computing device trains a classifier algorithm to identify the training images as semantically similar to one another based on the training images being grouped together. The trained classifier algorithm is used to determine that an input image is semantically similar to an example tagged image. A tag is generated for the input image using tag content from the example tagged image based on determining that the input image is semantically similar to the tagged image.

Abstract: An image reading apparatus comprising: an original reading unit configured to read an image of each of multiple originals placed on an original table in batch by a batch-scan; a cropping unit configured to crop an image of each original from an entire image which is read by the batch-scan; an image output unit configured to output a cropped image of each original; and a control unit configured to control the original reading unit, the cropping unit, and the image output unit, wherein the control unit makes the original reading unit read the image by a batch-scan in which an image density of an edge of each original is supposed to be lower than an image density of a reading-area outside of the original, and an area to be cropped is determined on the basis of a difference in the image density between the edge and the reading-area outside of the original.

Abstract: A monolithic display/projector is disclosed comprising a single die having an array of mechanically isolated LED pillars. Each pillar has a height greater than its width, and a pitch between pillars is less than the heights of the pillars. The die comprises an LED display portion bonded to a silicon substrate addressing portion, with one metal contact per pixel. The resolution of the display is preferably about the same as the resolution of the human retina when projected onto the human retina so that the image projected onto the retina may be indistinguishable from the real world. The display may be encapsulated into a contact lens with a focusing optic embedded into the contact lens. To electrically contact the N-type semiconductor layer, the pillars are surrounded by a reflective cathode metal mesh so that the cathode current is coupled through the vertical sides of the N-type layer. The metal mesh mechanically connects the isolated LED pillars and optically isolates each LED pillar.

Abstract: Systems and methods for transcribing and redacting a media is provided. One of the systems comprises: a transcription module configured to: receive the media content; transcribe the media content to create a transcript; a correlation module to correlate one or more words in the transcript to a start and end points in the media content; and a redaction module configured to: receive one or more candidate words to be redacted; and matching the received one or more candidate words to the one or more words in the transcript and identifying start and end points in the media; and redact one or more portions of the media content using the identified start and end points.

Abstract: A photographing method includes entering the slow shutter photographing mode, dividing each frame of image of the photographed object into a light trail region, a background light source region, and a non-light-source region, merging the light trail regions of the frames of images, setting a merged light trail region as a light trail region of a target image, setting the background light source regions of one or more of the frames of images as a background light source region of the target image to avoid overexposure, merging the non-light-source regions of one or more of the frames of images, setting a merged non-light-source region as a non-light-source region of the target image to enhance brightness of the non-light-source region, and storing the target image after obtaining a photographing instruction.

Abstract: Generating a plurality of event clusters by segmenting an image set. Each event cluster includes at least one image from the image set. The image set, having time metadata corresponding to each image in the set, is accessed. A time interval between each pair of neighboring images in the image set is determined. The neighboring images in each of the pairs are adjacent in a time ordered sequence. The time interval for each of the pairs is determined from time metadata associated with each image in the pair. An adjustment value is determined for one or more of the determined time intervals based on at least one of predetermined time of day information and calendar information. The images in the image set are segmented to generate the plurality of event clusters. Segmentation boundaries for each event cluster are determined using at least the determined adjustment value.

Abstract: In order to capture entire object, it is necessary for an image capturer to move a mobile terminal in various directions and to determine whether all is captured, and therefore, the operation of the image capturer becomes complicated. An information processing apparatus having a camera function, which displays a live view image acquired via a camera on a display, determines, by analyzing the live view image, a direction of an uncaptured area that should be captured next and whether the live view image is an image suitable to OCR processing, and displays, in accordance with analysis results of the live view image, a guide to prompt a user to perform an operation so that an image corresponding to the determined direction of the uncaptured area of the object is captured next.

Abstract: The present specification relates to a method for performing, by a first device, scanning in a wireless communication system, comprising the steps of: receiving a scan request which orders at least one neighboring device to perform scanning; and performing the scan negotiation procedure with a second device. According to the present specification, it is possible to enable a device with an insufficient energy source to perform a scanning function at lower power than a conventional wireless communication technique by performing a search function by another device.

Abstract: Disclosed is a method and system for generating redacted video of a scene captured using a video camera and augmenting a manual review process of the redacted video of the scene. According to an exemplary embodiment, a video of the scene is redacted via probability-based analysis to detect and obscure privacy sensitive objects included in the captured video. A manual review process of the generated redacted video is augmented to use the object detection probability to enhance the reviewing video frame rate to expedite the manual review process.

Abstract: Some implementations disclosed herein provide techniques and arrangements to enable translating language characters in media content. For example, some implementations receive a user selection of a first portion of media content. Some implementations disclosed herein may, based on the first portion, identify a second portion of the media content. The second portion of the media content may include one or more first characters of a first language. Some implementations disclosed herein may create an image that includes the second portion of the media content and may send the image to a server. Some implementations disclosed herein may receive one or more second characters of a second language corresponding to a translation of the one or more first characters of the first language from the server.

Abstract: A system and method for text line detection are described Examples include detection of symbols in an image received from an image-capturing device. In examples, for each of at least some of the symbols, neighboring symbols within a local region a given distance from the symbol are analyzed in order to determine a direction for a line in the local region. In examples, based on the determined directions for the lines, text lines in the image are identified.

Abstract: An example electronic device includes a watermark scanner to scan a watermark embedded on an initial page of a physical medium. The electronic device also includes a gesture sensor to detect a hand movement of a consumer associated with the physical medium. The electronic device further includes a controller to: determine a page number of the initial page based on the scanned watermark; determine a current page number based on the page number of the initial page; determine a page number of a subsequent page of the physical medium based on the detected hand movement and the current page number; and determine payoff information associated with the subsequent page based on the page number of the subsequent page.

Abstract: A decoder adapted to generate an intermediate decoded version of a video frame from an encoded version of the video frame, determine either an amount of high frequency basis functions or coefficients below a quantization threshold for at least one block of the video frame, and generate a final decoded version of the video frame based at least in part on the intermediate decoded version of the video frame and the determined amount(s) for the one or more blocks of the video frame, is disclosed. In various embodiments, the decoder may be incorporated as a part of a video system.

Abstract: A method for removing a mark in a document image includes: extracting connected components from a binary image corresponding to the document image; clustering the connected components based on grayscale features of the connected components to obtain one clustering center; searching, within numerical ranges of a clustering radius R and a grayscale threshold T, for a combination (R, T) which causes an evaluation value based on the grayscale features of the connected components to be higher than a first evaluation threshold; and removing the mark in the document image based on the grayscale threshold in the combination. The method and an apparatus according to the invention can remove a mark in a document image effectively and accurately.

Abstract: A display apparatus and a method for controlling thereof are provided. The display apparatus includes a first display configured to display content, a second display configured to display an image at an outer area of the first display, and a controller configured to, in response to input of a user command while content is displayed on the first display, display a User Interface (UI) to control the display apparatus on the second display, and control content of the display by using the UI to control the display apparatus.

Abstract: Apparatus and method for performing accurate text recognition of non-simplistic images (e.g., images with clutter backgrounds, lighting variations, font variations, non-standard perspectives, and the like) may employ a machine-learning approach to identify a discriminative feature set selected from among features computed for a plurality of irregularly positioned, sized, and/or shaped (e.g., randomly selected) image sub-regions.

Abstract: An image processing apparatus includes a subject area detector and a subject area determinator. The subject area detector is configured to perform subject detection processing to detect a subject area from an input image. The subject area determinator is configured to determine a final subject area by majority decision processing that is based on the subject areas detected in the subject detection processing performed a plurality of times.

Abstract: System and techniques for automatic video summarization are described herein. A video may be obtained and a semantic model of the video may be generated from frames of the video. Respective relevancy scores may be assigned to the frames. The semantic model may be initialized with the respective relevancy scores. The semantic model may then be iteratively processed to produce sub-scenes of the video, the collection of sub-scenes being the video summarization.

Abstract: An image is passed through an image identifier to identify a coarse category for the image and a bounding box for a categorized object. A mask is used to identify the portion of the image that represents the object. Given the foreground mask, the convex hull of the mask is located and an aligned rectangle of minimum area that encloses the hull is fitted. The aligned bounding box is rotated and scaled, so that the foreground object is roughly moved to a standard orientation and size (referred to as calibrated). The calibrated image is used as an input to a fine-grained categorization module, which determines the fine category within the coarse category for the input image.

Abstract: An image processing apparatus includes a fluorescence pixel detecting unit, a peripheral pixel analyzing unit, and an image processing unit. The fluorescence pixel detecting unit is configured to detect a fluorescence pixel that has a fluorescent color in a document image. The peripheral pixel analyzing unit is configured to detect consecutive non-fluorescence pixels with no fluorescent colors among peripheral pixels within a predetermined range from the detected fluorescence pixel. The consecutive non-fluorescence pixels is at least a predetermined number of consecutive pixels and has a color difference equal to or less than a predetermined value between one and another of the consecutive non-fluorescence pixels. The image processing unit is configured to perform an emphasizing process of improving visibility for the detected consecutive non-fluorescence pixels.

Abstract: Aspects of the present invention are related to systems and methods for estimation of additive noise in an image or in a video sequence. An additive-noise estimate may be computed based on a first significant peak in a histogram of standard-deviation values of patches of an image-channel image associated with an input image.

Abstract: A method for encoding and decoding a digital image signal, and associated devices. A method for encoding a digital image signal represented by a set of digital samples includes applying a segmentor to a reference digital image signal to obtain subsets of digital samples and applying a same filter among a set of predetermined filters to each sample of a subset of digital samples. The method includes a step of selecting (S320) a subset of segmentors from a predetermined set of segmentors based upon at least one characteristic obtained from the reference digital image signal, and a step (S330) of determining one segmentor among the selected subset of segmentors to apply to the reference digital image signal. Advantageously, a large initial set of segmentors can be used, the selection of a subset allowing to limit the computational complexity and adapt the segmentor to the reference digital image to be filtered.

Abstract: The present invention discloses a processing system and method for the scanning content. The processing system for the scanning content includes a scanning device and a cloud processing device. The scanning device scans the image of the non-electronic paper to generate a paper image and retrieves a selected content image corresponding to the selected content from the paper image. The cloud processing device analyzes the selected content image to correspondingly generate a content type, obtains a processing mode table which stores a plurality of content types and processing means corresponding to each content type, determines which content type in the processing mode table the generated content type belongs to and executes the processing means corresponding to the content type.

Abstract: An image processing apparatus determines, when image data of an image read from an original is transmitted to an external unit, whether the transmission is by a first communication method or a second communication method, and controls so that, based on a result of the determination, a transmission interval between a plurality of packets for when the image data is transmitted is longer when the image data is transmitted by the first communication method than when the image data is transmitted by the second communication method.

Abstract: In some embodiments, a recognition result produced by a speech processing system based on an analysis of a speech input is evaluated for indications of potential errors. In some embodiments, sets of words/phrases that may be acoustically similar or otherwise confusable, the misrecognition of which can be significant in the domain, may be used together with a language model to evaluate a recognition result to determine whether the recognition result includes such an indication. In some embodiments, a word/phrase of a set that appears in the result is iteratively replaced with each of the other words/phrases of the set. The result of the replacement may be evaluated using a language model to determine a likelihood of the newly-created string of words appearing in a language and/or domain. The likelihood may then be evaluated to determine whether the result of the replacement is sufficiently likely for an alert to be triggered.

Abstract: A method for proactively creating an image product includes storing a library of specification terms for image products by a computer system, receiving a command from a user, tokenizing the command into a plurality of tokens by the computer system, matching one or more of the tokens to the specification terms in the library to determine specification parameters for an image product by the computer system, automatically identifying images based on the specification parameters by the computer system, and automatically creating a design for the image product that incorporates at least some of the images identified based on the specification parameters.

Abstract: An algorithm (such as the MD5 hash function) is applied to a file to produce an intrinsic unique identifier (IUI) for the file (or message digest). The file is encrypted using its IUI as the key for the encryption algorithm. An algorithm is then applied to the encrypted file to produce an IUI for the encrypted file. The encrypted file is safely stored or transferred within a network and is uniquely identifiable by its IUI. The encrypted file is decrypted using the IUI of the plaintext file as the key. The IUI serves as both a key to decrypt the file and also as verification that the integrity of the plaintext file has not been compromised. IUIs for any number of such encrypted files may be assembled into a descriptor file that includes meta data for each file, the IUI of the plaintext file and the IUI of the encrypted file. An algorithm is applied to the descriptor file to produce an IUI for the descriptor file.

Abstract: In some embodiments, the recognition results produced by a speech processing system (which may include two or more recognition results, including a top recognition result and one or more alternative recognition results) based on an analysis of a speech input, are evaluated for indications of potential significant errors. In some embodiments, the recognition results may be evaluated to determine whether a meaning of any of the alternative recognition results differs from a meaning of the top recognition result in a manner that is significant for a domain, such as the medical domain. In some embodiments, words and/or phrases that may be confused by an ASR system may be determined and associated in sets of words and/or phrases. Words and/or phrases that may be determined include those that change a meaning of a phrase or sentence when included in the phrase/sentence.

Abstract: A method for receiving user inputs in a system comprising a projector and a camera is provided. The method is based on determining an object's height above a reference surface. A surface map is used for mapping a location on the reference surface and a corresponding location in a camera-captured image having a view of the reference surface. In particular, a camera-observed shadow length, i.e. a length of the object's shadow observable by the camera, estimated by using the surface map, is used to compute the object's height above the reference surface (a Z coordinate). Whether or not the object touches the reference surface is also obtainable. After an XY coordinate is estimated, a 3D coordinate of the object is obtained. By computing a time sequence of 3D coordinates, the motional information, such as velocity and acceleration, is obtainable.

Abstract: An image-reading apparatus according to the present invention reads one or more documents to acquire a read image, detects edge coordinates of a document image closest to an outer edge of the read image in a plurality of certain directions, and regionally divides the read image in the certain directions based on any one or both of a region of the read image in which no edge coordinates are detected and the edge coordinates of an edge end of the detected document image.