63 results about "Document segmentation" patented technology

The present application provides an improved segmentation method and system for processing digital images that include an imaged document and surrounding image. A plurality of edge detection techniques are used to determine the edges of the imaged document and then segment the imaged document from the surrounding image.

A method for segmenting a color document into regions of text and halftone discriminates between text and halftone by examining the texture of the document. A color document is digitized, and a color space transform is preferably applied to the digitized document. The texture of the document is identified and a noise reduction step is preferably applied. Bounding boxes (blocks) within the document are identified and then the areas within the bounding boxes are classified as either text or halftone. Two alternative methods are described for examining the document texture. In the first method, a windowing operation is applied to either an intensity image or a color difference image. In the second method, a wavelet transform step combined with Fuzzy K-Mean clustering is applied. Bounding boxes are classified as either text or halftone based upon the relative periodicity of a horizontal or vertical (or both) histogram of each bounding box.

A document may be segmented based on a visual model of the document. The visual model is determined according to an amount of visual white space or gaps that are in the document. In one implementation, the visual model is used to identify a hierarchical structure of the document, which may then be used to segment the document.

Characteristics of text or text components or features are considered when selecting halftoning screens. For example, an italic slant angle of text is recognized and used to select or generate a compatible halftone screen oriented at the same angle. A screen frequency may be selected based on a thickness of a text component. Descriptive tags associated with text or text components facilitate screen selection. Tags are assigned based on font descriptions included in a document during authoring. Alternatively, tags are assigned based on the results of document segmentation and character recognition techniques. An image processing system operative to consider characteristics of text or text components when selecting halftone screens includes a text component characteristic recognizer, a halftone screen selector and a halftoner. Optionally a print engine is also included. In a xerographic environment the print engine includes a xerographic printer.

A method of document segmentation. Specifically, one embodiment of the present invention discloses a method of document segmentation that performs a plurality of projection profiles of pixel intensities on a document containing a plurality of text lines over a range of angles. A plurality of slope values for a plurality of discrete distances perpendicular to said range of angles is calculated for the plurality of projection profiles. A set of maximum absolute slope values is sorted out from the plurality of slope values. Text lines of first and second type are identified by setting a threshold slope value. Absolute slope values greater than the threshold slope value indicate the plurality of text lines of said first type. Absolute slope values less than the threshold slope value indicate the plurality of text lines of a second type.

A method for extracting of data contained in a fixed format electronic document is disclosed. The method is particularly applicable to extracting data from tables in electronic documents and includes reading, by a computer system, the electronic document as a computer image file; segmenting, by the computer system, the computer image file into document sections representative of distinct portions of data; applying a label to each distinct document section; and executing, by the computer system, an optical character recognition algorithm to convert the image file into computer-readable text, wherein segments of the converted text is associated with a respective label indicative of each distinct document section.

The invention discloses a morphology and integral projection-based printed Uygur document segmentation method, and mainly solves the problem of flexibility limitation during acquisition of a row document image and the problem of missing segmentation of a character define in the specification during acquisition of a single-character image in an existing segmentation method. The method comprises the steps of (1) inputting a binary image; (2) acquiring the row document image; (3) acquiring a sub-word image; (4) acquiring a connected segment image; (5) acquiring a connected segment image only with a main body stroke part; (6) determining a baseline domain of the connected segment image only with the main body stroke part; and (7) acquiring the single-character image. Compared with an existing printed Uygur document segmentation method, the morphology and integral projection-based printed Uygur document segmentation method has the advantages that a threshold is not set during the acquisition of the row document image, so that the flexibility is better, the problem of the missing segmentation of the character define in the specification is avoided, and the accuracy of printed Uygur document segmentation can be improved.

The invention relates to a picture file encryption and decryption method and a picture file encryption and decryption system based on a content-associated secret key. When in encryption, according to the importance of data with respect to file application, the original picture file is segmented into sensitive data and main body data, the sensitive data forms a secret key, the main body data is subjected to supplemental treatment to form a cryptograph, and the secrete key and the cryptograph are respectively transmitted via different ways, and then combined at a destination to revert to the original picture file when in decryption; when the original picture file is segmented, the segmentation operation of the picture file is performed in a file layer, and the segmentation operation is performed in pixels based on a pixel gray level value or the contour line of a monochromatic chromatic value. According to the new encryption mechanism based on the content-associated secret key provided by the invention, the secret key with large data volume can be used, and the encryption and decryption processes are basically performed on the client, thus the system load is not increased; the new encryption mechanism can improve the data safety of the cloud storage system, in particular enhancing the privacy of the user data.

The invention relates to the field of text processing. In view of the problems in the prior art, the invention provides a method and device for document segmentation based on text lines. Whether or not text line units are merged into one paragraph is judged according to a merged score of the text line units; when the score of the text line units does not satisfy a merging need, merging of a current paragraph is ended, and processing of a new paragraph begins. According to the method and device for the document segmentation based on the text lines, the problems existing in the prior art can be solved simply and effectively; pages and document data structures can be extracted by using the method, and text line information is extracted from the document data structure corresponding to each text line; each document data structure including text lines is traversed in a full text, and context information of the full text and context information of each page can be calculated in a statistical mode according to a text line information list formed by the text line information of the document data structures separately; based on n text line unit structure lists in each page, by combining other context information, segmentation is conducted on the text line units in each page according to a segmentation algorithm.

A user device associated with a user may receive a document associated with the user. The user device may encrypt the received document. The user device may perform patch-based document segmentation on the received document to form a plurality of patches on the received document. The user device may extract text from each patch of the plurality of patches. The user device may analyze the extracted text from each patch to detect a field title and a field value. The user device may encrypt the extracted text and its associated field value for each patch of the plurality of patches. The user device may send the encrypted extracted text and its associated field value to the user device and instructions to display the extracted text and its associated field value on a user interface.

The invention discloses a document updating method and a server. The method comprises the steps: generating a homomorphic calculation function and a homomorphic parameter according to to-be-updated content information, and the to-be-updated content information is the information obtained through the comparison of an original document and a to-be-updated document; determining an identifier of a to-be-updated sub-file according to the to-be-updated content information, the to-be-updated sub-file being a to-be-updated file in the segmentation sub-file, and the segmentation sub-file being a file obtained by segmenting the original document; updating parameters are generated according to the homomorphic calculation function, the parameter encryption result and the identifiers and numbers corresponding to the to-be-updated sub-files, and the parameter encryption result is obtained by homomorphic encryption of the homomorphic parameters through adoption of a homomorphic encryption public key;and sending the update parameters to the blockchain network, so that the storage node server updates the segmentation sub-files stored by the storage node server according to the update parameters. And the working efficiency is improved, and resource waste is avoided.

The invention provides a cloud printing large document rapid printing method. The cloud printing large document rapid printing method comprises a client, a document server, a mobile terminal and a printing terminal, wherein each terminal is in network connection with the server; the client transmits a to-be-printed document to a conversion assembly, and performs document conversion and segmentation processing after detecting a large document message; the document server receives and stores the converted document uploaded by the client; the mobile terminal is associated with the client accountinformation, obtains the to-be-printed document, and is associated with the printing terminal by scanning a QR code of the printing terminal, so as to submit the to-be-printed document; and the printing terminal receives the to-be-printed document and prints the document. And the conversion assembly integrated by the client comprises a control end and a processing end and is used for converting and processing the large document. When a printer receives a large document printing command, document segmentation can be automatically carried out and then the documents are printed sequentially, thussolving the problems that the printing speed is low, and the waiting time of a user is long and the like, and improving the printing efficiency.

A document segmentation method of detecting segmentation points where a topic of an input document is discontinuous before and after the point to divide the document into plural blocks includes: detecting terms that occur in an input document; segmenting the input document into document segments, each segment being an appropriate sized chunk; generating document segment vectors with as its elements values related to frequencies of the terms occurring in the document segments; calculating eigenvalues and eigenvectors of a square sum matrix of the document segment vectors; selecting the basis vectors consisting a subspace from the eigenvectors to calculate the topic continuity of the document segments; calculating vectors with as their elements the values corresponding to the projection values of the each document segment vector onto the basis vector; and determining segmentation points of the document based on the continuity of the projected vectors.

A method, system and a computer program product are provided for collecting document segmentation data by activating a document segmentation collection browser plugin with a designated toolbar button to generate one or more initial document segments from a webpage document and to receive user feedback for modifying a first initial document segment through a document segment control tool to generate a modified set of one or more initial document segments which are stored as document and document preprocessing data for the webpage document.