Abstract: The disclosure provided live streaming interface display method, device, apparatus, storage medium and program product. The method comprises displaying a live streaming interface, wherein the live streaming interface comprises an identification area, the identification area comprises at least one scene identification, and each scene identification is used for indicating a live streaming scene; in response to a first input on a first scene identification of the at least one scene identification, displaying at least one first data source identification corresponding to the first scene identification in the identification area, wherein the first scene identification is used for indicating a first live streaming scene, and each first data source identification is used for indicating one data source in the first live streaming scene.

Abstract: An image processing device includes a storage device that previously stores a document image, a plurality of registered words, and a plurality of font characters, and a control device that functions as: a character region identifier that identifies a character region in the document image; an image acquirer that acquires an image of the character region; a text extractor that extracts a text from the image of the character region; a word identifier that identifies each of words in the text; a word determiner that determines whether each of the words is matched with one of the registered words; and a generator that generates a corrected text by replacing a target character of a non-matching word in the text with, among the font characters, a font character having a first degree of matching not lower than a first rate with the target character and a highest first degree of matching.

Abstract: A device receives information indicating first names and last names of individuals and applies different cursive fonts to each of the first names and the last names to generate images of different cursive first names and different cursive last names. The device applies different transformations to the images of the different cursive first names and the different cursive last names to generate a set of first name images and a set of last name images. The device combines each first name image with each last name image to form a set of signature images and trains a neural network model, with the set of signature images, to generate a trained neural network model. The device receives an image of a signature and processes the image of the signature, with the trained neural network model, to recognize a first name and a last name in the signature.

Abstract: A method, an apparatus, a device, a storage medium and a program product of performing a text matching are provided, which relate to a field of a computer technology, and in particular to natural language processing and deep learning technologies. The method includes: determining a word set and a plurality of semantic units from a text set, the word set is associated with a first predetermined attribute, and the text set contains a plurality of first texts indicating an object information and a plurality of second texts indicating an object demand information; generating a graph; and generating a final feature representation associated with the text set and the word set based on the graph and a graph convolution model, so as to perform the text matching.

Abstract: The present disclosure determines whether or not a character string of a result obtained by a character recognition process matches a word of a word dictionary; and when a pattern that is similar to a predefined arrangement pattern of a character type is present in the character string of the result obtained by the character recognition process that is determined not to match a word of the word dictionary, changes the character recognition process for the character string based on the pattern.

Abstract: A system of multi-modal transmission of packetized data in a voice activated data packet based computer network environment is provided. A natural language processor component can parse an input audio signal to identify a request and a trigger keyword. Based on the input audio signal, a direct action application programming interface can generate a first action data structure, and a content selector component can select a content item. An interface management component can identify first and second candidate interfaces, and respective resource utilization values. The interface management component can select, based on the resource utilization values, the first candidate interface to present the content item. The interface management component can provide the first action data structure to the client computing device for rendering as audio output, and can transmit the content item converted for a first modality to deliver the content item for rendering from the selected interface.

Abstract: The disclosure provides a method and a device for processing information, an electronic device, and a storage medium, belonging to a field of artificial intelligence including computer vision, deep learning, and natural language processing. In the method, the computing device recognizes multiple text items in the image. The computing device classifies multiple text items into a first set of name text items and a second set of content text items based on semantics of the text items. The computing device performs a matching operation between the first set and the second set based on a layout of the text items in the image, and determines matched name-content text items. The matched name-content text items include a name text item in the first set and a content text item matching the name text item and in the second set. The computing device outputs the matched name-content text items.

Abstract: Techniques are provided for generating a digital image of simulated handwriting using an encoder-decoder neural network trained on images of natural handwriting samples. The simulated handwriting image can be generated based on a style of a handwriting sample and a variable length coded text input. The style represents visually distinctive characteristics of the handwriting sample, such as the shape, size, slope, and spacing of the letters, characters, or other markings in the handwriting sample. The resulting simulated handwriting image can include the text input rendered in the style of the handwriting sample. The distinctive visual appearance of the letters or words in the simulated handwriting image mimics the visual appearance of the letters or words in the handwriting sample image, whether the letters or words in the simulated handwriting image are the same as in the handwriting sample image or different from those in the handwriting sample image.

Abstract: A text recognition method and apparatus disclosed. The text recognition method includes: obtaining a to-be-detected image; determining a target text detection area in the to-be-detected image, where the target text detection area includes target text in the to-be-detected image, and the target text detection area is a polygonal area including m vertex pairs, m being a positive integer greater than 2; correcting the polygonal area to m?1 rectangular areas to obtain a corrected target text detection area; and performing text recognition on the corrected target text detection area to determine the target text, and outputting the target text.

Abstract: Disclosed is a method for error detection, performed by one or more processors of a computing device according to an example embodiment of the present disclosure. The method includes evaluating an error rate for a sentence to be evaluated, in a first language unit. the method includes evaluating an error rate in a second language unit which is smaller than the first language unit, based on the first language unit error.

Abstract: This relates to intelligent automated assistants and, more specifically, to the intelligent coordination of audio signal output adjustments among multiple electronic devices.

Abstract: Methods, systems, devices, and tangible non-transitory computer readable media for generating assistive indications are provided. The disclosed technology can include accessing image data that includes at least one image. Character data can be generated based at least in part on the image data and one or more optical character recognition operations. Further, the character data can include one or more characters associated with the at least one image. One or more characters that are associated with one or more recognized words and the one or more characters that are associated with one or more unrecognized words can be determined based on the character data. One or more auditory indications including a synthetic voice reciting the one or more recognized words and the one or more unrecognized words can be generated. Furthermore, the synthetic voice can recite each of the one or more unrecognized words one character at a time.

Abstract: A method for estimating text heights of text line images includes estimating a text height with a sequence recognizer. The method further includes normalizing a vertical dimension and/or position of text within a text line image based on the text height. The method may also further include calculating a feature of the text line image. In some examples, the sequence recognizer estimates the text height with a machine learning model.

Abstract: A character recognizing apparatus includes an acquiring unit, an identifying unit, and a character recognizing unit. The acquiring unit acquires a string image that is an image of a string generated in accordance with one of multiple string generation schemes. The identifying unit identifies a range specified for a result of character recognition in each of the multiple string generation schemes. The character recognizing unit performs first character recognition on the string image, and if a result of the first character recognition has a feature of a particular string generation scheme of the multiple string generation schemes, the character recognizing unit performs second character recognition on the string image within the range specified for a result of character recognition in the particular string generation scheme.

Abstract: Described herein are systems, methods, and other techniques for training a generative adversarial network (GAN) to perform an image-to-image transformation for recognizing text. A pair of training images are provided to the GAN. The pair of training images include a training image containing a set of characters in handwritten form and a reference training image containing the set of characters in machine-recognizable form. The GAN includes a generator and a discriminator. The generated image is generated using the generator based on the training image. Update data is generated using the discriminator based on the generated image and the reference training image. The GAN is trained by modifying one or both of the generator and the discriminator using the update data.

Abstract: Methods and apparatus to determine the dimensions of a region of interest of a target object and a class of the target object from an image using target object landmarks are disclosed herein. An example method includes identifying a landmark of a target object in an image based on a match between the landmark and a template landmark; classifying a target object based on the identified landmark; projecting dimensions of the template landmark based on a location of the landmark in the image; and determining a region of interest based on the projected dimensions, the region of interest corresponding to text printed on the target object.

Abstract: Systems and methods are provided that distinguish humans from computers. In one implementation, a computer-implemented method selects, from a storage device, a plurality of images. The method further generates a document comprising the plurality of images for the security challenge. At least one image included in the plurality of images is oriented for display in a different direction than the other images. The method further receives a selection of one or more images included in the plurality of images and determines whether the selected one or more images is oriented for display in a different direction than the other images.

Abstract: A method for context-aware data mining of a text document includes receiving a list of words parsed and preprocessed from an input query; computing a related distributed embedding representation for each word in the list of words using a word embedding model of the text document being queried; aggregating the related distributed embedding representations of all words in the list of words to represent the input query with a single embedding, by using one of an average of all the related distributed embedding representations or a maximum of all the related distributed embedding representations; retrieving a ranked list of document segments of N lines that are similar to the aggregated word embedding representation of the query, where N is a positive integer provided by the user; and returning the list of retrieved segments to a user.

Abstract: There is provided an image processing apparatus including an input device configured to receive a stroke input, and a display controller configured to control a displaying of a modified stroke, wherein the modified stroke is synthesized based on characteristic parameters of the received stroke input and characteristic parameters of a reference stroke that has been matched to the received stroke input.

Abstract: The present disclosure relates to a method and a terminal for performing word segmentation on text information, and a storage medium. The method includes: acquiring the text information and configuration information, in which the configuration information includes at least two first word segmentation rules; converting the first word segmentation rules into second word segmentation rules according to a predetermined rule; in response to determining that an intersection exists between character strings of the text information matched by two of the second word segmentation rules, determining that two first word segmentation rules corresponding to the two of the second word segmentation rules associated with the intersection conflict; and processing the text information according to the configuration information, and outputting a result of the word segmentation on the text information.

Abstract: Systems and methods for receiving a set analyzing case records by extracting case text, performing natural language processing, and allocating each case text to a topic. Topics may be clustered to identify meaningful patterns that are reflected in numerous case records. The data resulting from the analysis may be visualized on a dashboard to allow users to identify and explore these patterns.

Abstract: According to one aspect of the invention, there is provided a method for searching for documents containing mathematical expressions, the method comprising the steps of: dividing a first document containing mathematical expressions into a plurality of components; comparing the plurality of components with a plurality of other components extracted from a plurality of other documents, with reference to weights respectively assigned to the plurality of components according to types of the components; and determining a document associated with the first document among the plurality of other documents, with reference to a result of the comparison, wherein the weights are adaptively adjusted according to a result of the determination of the document associated with the first document.

Abstract: System, method, and various embodiments for providing contextualized character recognition system are described herein. An embodiment operates by determining a plurality of predicted words of an image. An accuracy measure or each of the plurality of predicted words is identified and a replaceable word with an accuracy measure below a threshold is identified. A plurality of candidate words associated with the replaceable word are identified and a probability for each of the candidate words is calculated based on a contextual analysis. One of the candidate words with a highest probability is selected. The plurality of predicted words including the selected candidate word with the highest probability replacing the replaceable word is output.

Abstract: A picture obtaining method and apparatus and a picture processing method and apparatus are provided. The method includes: obtaining a grayscale image corresponding to a first picture and a first image, where a size of the first picture is equal to a size of the first image, the first image includes N parallel lines, a spacing between two adjacent lines does not exceed a spacing threshold, and N is an integer greater than 1; translating a pixel included in each line in the first image based on the grayscale image, to obtain a second image, where the second image includes a contour of an image in the first picture; and set a pixel value of each pixel included in each line in the second image, to obtain a second picture.

Abstract: Aspects of the present invention provide a new text location technique, which can be applied to general handwriting detection at a variety of levels, including characters, words, and sentences. The inventive technique is efficient in training deep learning systems to locate text. The technique works for different languages, for text in different orientations, and for overlapping text. In one aspect, the technique's ability to separate overlapping text also makes the technique useful in application to overlapping objects. Embodiments take advantage of a so-called skyline appearance that text tends to have. Recognizing a skyline appearance for text can facilitate the proper identification of bounding boxes for the text. Even in the case of overlapping text, discernment of a skyline appearance for words can help with the proper identification of bounding boxes for each of the overlapping text words/phrases, thereby facilitating the separation of the text for purposes of recognition.

Abstract: Techniques are provided for generating a digital image of simulated handwriting using an encoder-decoder neural network trained on images of natural handwriting samples. The simulated handwriting image can be generated based on a style of a handwriting sample and a variable length coded text input. The style represents visually distinctive characteristics of the handwriting sample, such as the shape, size, slope, and spacing of the letters, characters, or other markings in the handwriting sample. The resulting simulated handwriting image can include the text input rendered in the style of the handwriting sample. The distinctive visual appearance of the letters or words in the simulated handwriting image mimics the visual appearance of the letters or words in the handwriting sample image, whether the letters or words in the simulated handwriting image are the same as in the handwriting sample image or different from those in the handwriting sample image.

Abstract: The present disclosure proposes an end-to-end text recognition method and apparatus, computer device and readable medium. The method comprises: obtaining a to-be-recognized picture containing a text region; recognizing a position of the text region in the to-be-recognized picture and text content included in the text region with a pre-trained end-to-end text recognition model; the end-to-end text recognition model comprising a region of interest perspective transformation processing module for performing perspective transformation processing for the text region. The technical solution of the present disclosure does not need to serially arrange a plurality of steps, and may avoid introducing the accumulated errors and may effectively improve the accuracy of the text recognition.

Abstract: A method and system for generating a parsed document from a digital document. The method includes segmenting the digital document into at least one section; classifying the at least one section of the digital document into at least one of a class: text class, table class, figure class, noise class; identifying a reading order of the digital document; and processing each of the at least one section of the digital document. Furthermore, processing each of the at least one section of the digital document comprises extracting content from each of the at least one section based on the class; and structuring the extracted content based on the reading order to generate the parsed document.

Abstract: A method of identifying contiguities in images is disclosed. The contiguities are indicative features and various qualities of an image, which may be used for identifying objects and/or relationships in images. Alternatively, the contiguities may be helpful in ensuring that an image has a desired switching factor, so as to create a desired effect when combined with other images in a composite image. The contiguity may be a group of picture elements that are adjacent to one another that form a continuous image element that extends generally horizontally (e.g., diagonally, horizontally) across the image.

Abstract: Described herein are various technologies pertaining to text extraction from a document. A computing device receives the document. The document comprises computer-readable text and a layout, wherein the layout defines positions of the computer-readable text within a two-dimensional area represented by the document. Responsive to receiving the document, the computing device identifies at least one textual element in the computer-readable text based upon spatial factors between portions of the computer-readable text and contextual relationships between the portions of the computer-readable text. The computing device then outputs the at least one textual element.

Abstract: An information processing apparatus includes a first designation unit, a second designation unit, a position acquisition unit, a memory, and an extraction unit. The first designation unit designates an extensive area from a first read image, the extensive area including an output area and an object area. The second designation unit designates the output area from the designated extensive area. The position acquisition unit acquires positional information regarding the extensive area with respect to the first read image and positional information regarding the output area with respect to the extensive area. The memory stores the positional information regarding the extensive area and the positional information regarding the output area. The extraction unit identifies a position of the extensive area in a second read image in a format identical to a format of the first read image on a basis of the positional information regarding the extensive area stored by the memory.

Abstract: A computer implemented method includes receiving a document with line item textual entries and an attachment containing images of different objects characterizing different transactions. The images of the different objects are split into individual image objects. Attributes from the individual image objects are extracted. The line item textual entries are matched with the individual image objects to form matched image objects. The matched image objects include ambiguous matches with multiple individual image objects assigned to a single line item textual entry or a single individual image object assigned to multiple line item textual entries. An assignment model is applied to resolve the ambiguous matches. The assignment model defines priority constraints, assigns pairs of line item textual entries and individual image objects that meet highest priority constraints, removes highest priority constraints when ambiguous matches remain, and repeats these operations until no ambiguous matches remain.

Abstract: An information processing device according to an embodiment includes a determination unit and a first training unit. The determination unit determines whether an unlabeled data point whose class label is unknown is a non-targeted data point that is not targeted for pattern recognition. The first training unit trains a first classifier for use in the pattern recognition through semi-supervised learning using a first training dataset including unlabeled data determined not to be the non-targeted data and not including unlabeled data determined to be the non-targeted data.

Abstract: A method for extracting data from lineless tables includes storing an image including a table in a memory. A processor operably coupled to the memory identifies a plurality of text-based characters in the image, and defines multiple bounding boxes based on the characters. Each of the bounding boxes is uniquely associated with at least one of the text-based characters. A graph including multiple nodes and multiple edges is generated based on the bounding boxes, using a graph construction algorithm. At least one of the edges is identified for removal from the graph, and removed from the graph to produce a reduced graph. The reduced graph can be sent to a neural network to predict row labels and column labels for the table.

Abstract: The present invention relates to a device and a method for placing an original or translated explanation of a reference numeral around the reference numeral in a patent drawing, by recognizing a reference numeral included in a patent drawing, searching for a space to place an explanation corresponding to the recognized reference numeral, generating a placement information set including position information for displaying the explanation of the reference numeral in the searched empty space, and providing the placement information set to a corresponding patent drawing image. Utilization of the present invention makes it possible to recognize clearly and quickly what is represented by a reference numeral included in a patent drawing, thereby increasing the readability of a drawing, and facilitating understanding of the technical idea of a patent through patent drawings.

Abstract: A method for estimating text heights of text line images includes estimating a text height with a sequence recognizer. The method further includes normalizing a vertical dimension and/or position of text within a text line image based on the text height. The method may also further include calculating a feature of the text line image. In some examples, the sequence recognizer estimates the text height with a machine learning model.

Abstract: A system for automated user input alignment receives the user input at a touchscreen display. A skew of the user input is identified as the user input is being received at a touchscreen display. A skew correction is determined based on the identified skew. The skew correction is applied to the user input to align the user input on the touchscreen display. The skew correction applied in an automated alignment process that. The user input is displayed with the applied skew correction on the touchscreen display with improved efficiency and without user manipulation to perform the alignment.

Abstract: Examples of systems and methods for automatic population of electronic documents are described. In an example, a digital base document having the information to be populated in a data field of the electronic document may be obtained. From the digital base document a data item to provide the information may be extracted. Further, for the digital base document, a similarity score may be computed with respect to each document type defined in predefined mapping data, the predefined mapping data including, for each document type, a weight associated with data items occurring in the document type, the weight being associated based on the importance of the data item to the document. Based on the similarity score, a document type of the digital base document may be identified. Further, based on a position of the data item in the digital base document and the identified document type, the data field may be populated.

Abstract: An image forming apparatus includes an image reading unit, an extraction section, a character recognition section, a search section, an attachment section, and file storage. The image reading unit generates first image information. The extraction section extracts a specific area from the image base on the first image information. The character recognition section generates text information corresponding to information of a character string image included in the specific area. The search section searches for a webpage containing information relating to a meaning of a text indicated by the text information. The attachment section attaches link information of the webpage to the information of the character string image to generate second image information. The file storage section stores the second image information as a file therein. The specific area is an area with a specific mark applied thereto.

Abstract: A method and apparatus for training a character detector based on weak supervision, a character detection system and a computer readable storage medium are provided, wherein the method includes: inputting coarse-grained annotation information of a to-be-processed object, wherein the coarse-grained annotation information including a whole bounding outline of a word, text bar or line of the to-be-processed object; dividing the whole bounding outline of the coarse-grained annotation information, to obtain a coarse bounding box of a character of the to-be-processed object; obtaining a predicted bounding box of the character of the to-be-processed object through a neural network model from the coarse-grained annotation information; and determining a fine bounding box of the character of the to-be-processed object as character-based annotation of the to-be-processed object, according to the coarse bounding box and the predicted bounding box.

Abstract: An information processing device includes a display controller that displays a term expression expressing a term which appears in target data, on a display in a display mode based on a level of liveliness of the target data when the term appears.

Abstract: In an optical character recognition system, a word segmentation method, comprising: acquiring a sample image comprising a word spacing marker or a non-word spacing marker; processing the sample image with a convolutional neural network to obtain a first eigenvector corresponding to the sample image, a word spacing probability value and/or a non-word spacing probability value corresponding to the first eigenvector; acquiring a to-be-tested image, and processing the to-be-tested image with the convolutional neural network to obtain a second eigenvector corresponding to the to-be-tested image, a word spacing probability value or a non-word spacing probability value corresponding to the second eigenvector; and performing word segmentation on the to-be-tested image by using the just obtained word spacing probability value or the non-word spacing probability value.

Abstract: An information processing apparatus includes: a first extracting unit that extracts a position of a character entry box in an input image; a recognizing unit that recognizes a character string written in the character entry box; a calculating unit that calculates recognition accuracy of each of characters of the character string recognized by the recognizing unit; a first detector that detects that a value based on the recognition accuracy is equal to or larger than a preset threshold value; a second extracting unit that extracts a position of a circumscribed rectangle for each character of the character string in the input image; a second detector that detects contact of the circumscribed rectangle with the character entry box; and a display that displays the character string to be corrected on the basis of a result of detection by the first detector and a result of detection by the second detector.

Abstract: An approach is provided for an asymmetric evaluation of polygon similarity. The approach, for instance, involves receiving a first polygon representing an object depicted in an image. The approach also involves generating a transformation of the image comprising image elements whose values are based on a respective distance that each image element is from a nearest image element located on a first boundary of the first polygon. The approach further involves determining a subset of the plurality of image elements of the transformation that intersect with a second boundary of a second polygon. The approach further involves calculating a polygon similarity of the second polygon with respect the first polygon based on the values of the subset of image elements normalized to a length of the second boundary of the second polygon.

Abstract: A new segment of electronic handwriting is provided to a handwriting recognition module to obtain a plurality of textual interpretations of the new segment. The textual interpretations obtained from the handwriting recognition module are scored based on how each respective electronic handwriting representation would change a display of existing electronic content when the respective electronic handwriting representation is displayed substantially at the user designated position within or adjacent to the existing electronic content. Based on the scoring, an electronic handwriting representation corresponding to a respective textual interpretation of the plurality of textual interpretations is selected, and the existing electronic content is modified to include the selected electronic handwriting representation located substantially at the user designated position.

Abstract: The present disclosure relates to a system and method to transform character images from one representation to another representation. According to some embodiments of the present disclosure, a form may be processed to separate background data from content data, wherein character images from one or both the background data and the content data may be transformed. In some aspects, one or both handwritten font and type font may be processed in the character images, wherein the original fonts may be transformed into a uniform type font. In some embodiments, the character images may be translated to their correct state, wherein the translation may occur before or after the transformation. In some implementations, the translation and font transformation may allow for more efficient and effective character recognition.

Abstract: The positioning of elements of a broken word can be corrected by receiving an optical character recognition (OCR) conversion of a printed publication and identifying multiple parts of the broken word from the OCR conversion to output in a graphical user interface (GUI). The multiple parts can be placed in the GUI using original positioning data for the printed publication. A user can make a selection in the GUI indicating that multiple parts from the OCR conversion are of the broken word and can automatically adjust bounds of the multiple parts to form a corrected word.

Abstract: A machine learning method for learning how to form bounding boxes, performed by a machine learning apparatus, includes extracting learning images including a target object among a plurality of learning images included in a learning database, generating additional learning images in which the target object is rotated from the learning images including the target object, and updating the learning database using the additional learning images.

Abstract: An image processing apparatus including: a processor; and memory storing computer-readable instructions therein, the computer-readable instructions, when executed by the processor, causing the image processing apparatus to perform: acquiring target image data configured by a plurality of pixels and representing a target image including a character; acquiring a character code corresponding to the character in the target image; acquiring an index value relating to a number of a plurality of character pixels configuring the character in the target image by using the character code corresponding to the character in the target image; determining a first extraction condition by using the index value; and extracting the plurality of character pixels satisfying the first extraction condition from the plurality of pixels in the target image.

Abstract: Systems and methods for digitized document image data spillage recovery are provided. One or more memories may be coupled to one or more processors, the one or more memories including instructions operable to be executed by the one or more processors. The one or more processors may be configured to capture an image; process the image through at least a first pass to generate a first contour; remove a preprinted bounding region of the first contour to retain text; generate one or more pixel blobs by applying one or more filters to smudge the text; identify the one or more pixel blobs that straddle one or more boundaries of the first contour; resize the first contour to enclose spillage of the one or more pixel blobs; overlay the text from the image within the resized contour; and apply pixel masking to the resized contour.