106 results about "Document image processing" patented technology

Techniques for assuring the quality of mobile document image captured using a mobile device are provided. These techniques include performing one or more tests to assess the quality of images of documents captured using the mobile device. The tests can be selected based on the type of document that was imaged, the type of mobile application for which the image quality of the mobile image is being assessed, and / or other parameters such as the type of mobile device and / or the characteristics of the camera of the mobile device that was used to capture the image. The image quality assurance techniques can also be implemented on can be implemented on a mobile device and / or on a remote server where the mobile device routes the mobile image to the remote server processing and the test results are be passed from the remote server to the mobile device.

A document image processing apparatus includes an image capturing unit for capturing an image of a document, a detecting unit for detecting focusing and twisting states of the capture image, a display unit for displaying the detected focusing and twisting states, a character recognition unit for recognizing characters written on the capture image, and a storing unit for storing the recognized characters by fields.

Techniques for assuring the quality of mobile document image captured using a mobile device are provided. These techniques include performing one or more tests to assess the quality of images of documents captured using the mobile device. The tests can be selected based on the type of document that was imaged, the type of mobile application for which the image quality of the mobile image is being assessed, and / or other parameters such as the type of mobile device and / or the characteristics of the camera of the mobile device that was used to capture the image. The image quality assurance techniques can also be implemented on can be implemented on a mobile device and / or on a remote server where the mobile device routes the mobile image to the remote server processing and the test results are be passed from the remote server to the mobile device.

The invention relates to an automatic recognition method of a mathematical formula in an image, which comprises the steps that: a syntactic structure model of the mathematical formula is built, and a bottom knowledge base of the mathematical formula is built; the location of the mathematical formula in the image, the recognition of a mathematical symbol, the analysis and comprehension of a mathematical formula structure and the expression and formatted output of the mathematical formula structure are carried out. The automatic recognition method designs a complete set of method and model for solving the recognition and comprehension difficulties of an off-line mathematical formula image and forms a method for automatically processing the mathematical formula image in the whole process. The method can realize the automatic judgment and extraction of an individual-line / embedded mathematical formula in an image, thereby meeting the application requirements of the automatic inputting of the mathematical formula image and the comprehension and format recurrence of the mathematical formula structure. The method can be combined with the existing normal text OCR system to form a document image processing system with more complete functions and also can support the research on expression processing methods in other fields, such as automatic processing aiming at chemical equations, etc.

Methods and systems that dynamically control and / or direct document image processing based on one or more of client device display capabilites, image formats supported by the client device, network bandwidth, document file format, document content and user hints.

A document image processing device and method for extracting a title region and a mark attached by the user from a document image to use them as document tag information. A region with a region average character size larger then a predetermine extraction judging value is extracted as a title region by title region extracting means. As a result, title regions can be extracted from one document image. A mark that the user makes on an input image is extracted by mark extracting means, and characteristic value of the mark is found by calculating means. Document tag information to be imparted to the input image is selected from reference tag information according to the characteristic value and the attribute value of the reference tag information imparting means. Thus, document tag information is automatically imparted to a document image.

A system and method are provided for processing a document image using color highlighting. The method comprises: scanning a document, creating a document image; searching the document image for a color-highlighted area; processing the document image with optical character recognition (OCR), creating a text document; identifying a text phrase associated with the color-highlighted area; searching the text document for the identified text phrase; and, tracking each area in the document image associated with the identified text phrase. Searching the document image for a color-highlighted area includes supplying a coordinate associated with the color-highlighted area. A text phrase in the text document is identified in response to locating the text phrase at the color-highlighted area coordinates. Tracking each area in the document image associated with the identified text phrase includes: tracking the coordinates of each identified text phrase in the text document; and, transposing the coordinates to the document image.

A method for detecting the most likely source of an error in a document image processing system which processes sets of related documents. A set of characteristics is selected as being indicative that the document image, or item, is the source of the error. Each of the characteristics is assigned a weight, wherein the weight is in proportion to the likelihood that an item exhibiting the characteristic is the source of error. The items are ranked according to the characteristics exhibited by each item.

An image of a character string composed of M pieces of characters is clipped from a document image, and the image is divided into separate characters. Image features of each character image are extracted. Based on the image features, N (N>1, integer) pieces of character images in descending order of degree of similarity are selected as candidate characters, from a character image feature dictionary which stores the image features of character image in units of character, and a first index matrix of M×N cells is prepared. A candidate character string composed of a plurality of candidate characters constituting a first column of the first index matrix, is subjected to a lexical analysis according to a language model, and whereby a second index matrix having a character string which makes sense is prepared. In the language model, statistics are taken and then, the lexical analysis is performed.

An image of a character string composed of M pieces of characters is clipped from a document image, and the image is divided character by character, and image features of each character image are extracted. On the basis of the image features, N (N>1, integer) pieces of character images in descending order of degree of similarity are selected as candidate characters from a character image feature dictionary which stores the image features of character image in units of character, and the first index matrix of M×N cells is prepared. A candidate character string composed of a plurality of candidate characters constituting the first column of the first index matrix, is subjected to a lexical analysis according to a predetermined language model, whereby a second index matrix adjusted into a character string which makes sense is prepared to he utilized for searching.

An image deblurring method for camera-based document image processing is described. A document image captured by a digital camera is divided into multiple overlapping or non-overlapping sub-images. A point spread function is derived for each sub-image by analyzing the gradient information along edges contained in the sub-image. Each sub-image is deblurred by using its local point-spread function. The whole deblurred image is constructed from deblurred sub-images. In cases where information of interest is located in localized parts of the document image, dividing the image into sub-images may be done by extracting the area of interest from the captured image. This deblurring method improves the quality of the deblurred image when the camera-captured image is blurred by variable amount of location-dependent defocus.

This invention relates to a tilt rapid detection method of complex structure document image, belongs to document image processing field. This invention first extracts the borders of connected region between the text and non-text region from the image, then through the filter of extracted border to obtain rubang border and corresponding tilt angle, get the tilt angle of the whole image through weighted medium value. It is showed through numerous experiments that the algorithm has the characteristics of fast, high precision, with wide range of applications.

Techniques for monitoring of storage usage and trends in a document image processing and storage system are described. A storage and retrieval monitor resides on a storage server and monitors the status of volumes and units on which data is stored, completed storage requests and pending storage and retrieval requests. The storage and retrieval monitor analyzes completed and pending storage requests in order to project usage trends over time, and also analyzes the storage status in order to determine the used and available space and the space dedicated to various units and classes of data such as documents and families of documents. The storage and retrieval monitor generates alerts when the available storage space falls below a predetermined limit. The alerts and the usage and status information are presented to a user through a user interface allowing easy access to the storage and usage information and the ability to select desired information for display.

What is disclosed is a novel system and method for content-aware resizing of a digital image. To take advantage of the characteristics of various importance maps generated for the image using different operators such as, for example, gradient, entropy, probabilistic operators, and the like, a method is provided herein for combining generated pixel importance maps. The present method uses a weighted combination of pixel importance maps—one corresponding to each image operator, to produce a hybrid map for all the image. The image can then be resized based on this hybrid map. The present method provides a high degree of image resizing flexibility and has broad applicability across differing classes of images and applications such as display, printing, packaging, and other document image processing software performing document layout, image personalization, and the like.

The invention discloses a picture file processing method. The method comprises: saving at least two pictures in one picture file, and saving the configuration file of the picture file, and the configuration file contains the pictures stored in the picture file. Position information: when the picture is needed, obtain the position information of the picture in the picture file according to the configuration file, and obtain the picture from the picture file according to the position information. The invention also discloses a picture file processing system. By adopting the present invention, the efficiency of image file processing is improved, and the resource of system graphics device interface (GDI) is saved.

The invention provides a photovoltaic panel inspection system and an inspection method. The system comprises an unmanned aerial vehicle, an image collector, an unmanned aerial vehicle controller, a mobile device and a server; the unmanned aerial vehicle controls the image collector to capture pictures and downloads the pictures to the mobile device, and the pictures have GPS information; the mobile device stores an inspection route; the unmanned aerial vehicle communicates with the mobile device through the unmanned aerial vehicle controller, so as to obtain an inspection route and flies according to the route, and pictures are downloaded from the image collector and sent to the mobile device; the mobile device uploads the picture to the server; and the server processes the picture to obtain a fault point, feeds the fault point back to the mobile device for display, and dispatches maintenance information. Compared with the prior art, the system does not need personnel participation inthe whole process from front-end user control to front-end image acquisition to rear-end image processing. The user manages the inspection work through the control end, so that the intelligence and intelligence of the power station are improved.

Various embodiments herein each include at least one of systems, methods, devices, and software for secure image processing. In particular, the secure image processing may be performed with regard to images, such as image frames of a video stream, from a camera to obscure, either via image modification, encryption, and discarding image frames, to prevent, limit, or secure viewing of sensitive information that may be included within images. One such embodiment includes receiving an image of an image flow from a scanner, such as a product scanner, and determining whether a sensitive item is present in the image. When a sensitive item is determined to be present in the image, such embodiments perform a security action with regard to the image prior to passing the image in the image flow from the scanner.

Techniques for assuring the quality of mobile document image captured using a mobile device are provided. These techniques include performing one or more tests to assess the quality of images of documents captured using the mobile device. The tests can be selected based on the type of document that was imaged, the type of mobile application for which the image quality of the mobile image is being assessed, and / or other parameters such as the type of mobile device and / or the characteristics of the camera of the mobile device that was used to capture the image. The image quality assurance techniques can also be implemented on can be implemented on a mobile device and / or on a remote server where the mobile device routes the mobile image to the remote server processing and the test results are be passed from the remote server to the mobile device.

There is provided a document image processing apparatus which can reduce troubles to find a desired heading from a document image. A heading region extracting portion searches an index information DB and extracts a heading region containing a search keyword. An order setting portion automatically sets in line with a predetermined rule an order of the heading regions extracted by the heading region extracting portion. On a displaying portion is displayed a document image on which the heading regions extracted by the heading region extracting portion are highlighted in accordance with the order set by the order setting portion. A display order of search results may be set by determining importance of the extracted heading regions based on the number of the search keyword and features of character images in the heading regions.

A character string of which the character number is M in a file image is extracted and separated into units one character by one character; the image feature of each character image is extracted; according to image features, Front feature dictionary 15 which stores the image features of the character images with 1 character as a unit is utilized; N (which is an integer larger than 1) character images are taken as alternative characters according to match degree in sequence from high to low; and a first index matrix of the character number of the extracted character string of M multiplied by Ndimensionality is created. The first index matrix created is made into a character combination to extract key words according to the definition analysis based on a conceptual dictionary. The extracted key words are displayed in a list according to the sequence based on required weight and statistic information.

The disclosure concerns systems and methods for extracting data from documents. A computer receives a message from a sender. The message has the electronic document and an electronic address of the sender. Based on the address of the sender the computer selects a map that comprises location data of data fields and determines values of the data fields by extracting data from the electronic document using the location data of the selected map. Since the computer selects the map based on the address of the sender the computer does not need to rely on the content of the electronic document to select the correct map to use, which makes the selection less prone to errors and the method can be used with existing email systems.

A document image processing apparatus includes an specifying section, an extracting section, a recognizing section, an interpreting section, an arranging section and a generating section. The specifying section specifies a sentence region including a character row from a document image. The extracting section extracts at least one of character row images included in the specified sentence region. The recognizing section recognizes respective characters included in the extracted character row image. The interpreting section interprets an original sentence character row comprising the recognized characters and generates an interpreted sentence character row. The arranging section arranges the respective character row images in the sentence region by contracting the respective character row images. The arranging section arranges the generated respective interpreted sentence character rows in a vacant region except a region arranging the respective character row images from the sentence region.

A method for processing a document image includes: performing horizontal and vertical text line extraction on the document image; providing an overlapping matrix, a value of an element of the overlapping matrix indicating an overlapping relation between horizontal and vertical text lines; merging the overlapping matrix in the vertical and horizontal direction; determining one or more text overlapping regions in the document image, based on the values of the elements of the merged overlapping matrix; counting the total number of strokes or pixel points in the horizontal and vertical text lines, respectively, within one of the one or more text overlapping regions; and determining an orientation of the text overlapping region is horizontal if the total number of strokes or pixel points in the horizontal text lines is larger than that in the vertical text lines, otherwise, determining the orientation is vertical.

The invention discloses a document image processing method, a storage medium and a computing device, and the method comprises the steps: firstly obtaining an original document image, extracting the document area edge of the original document image, and obtaining a first document area image; performing deformation correction on the first document area image to obtain a second document area image; performing brightness correction on the second document area image to obtain a third document area image; removing the document background color of the third document area image, and outputting a target document area image. The document area in the original document image can be accurately extracted, the document area image with the straight document area, uniform brightness and clear foreground characters is obtained, and the readability of the document area image can be improved.

An image of a character string composed of M pieces of characters is clipped from a document image, and the image is divided character by character, and image features of each character image are extracted. On the basis of the image features, N (N>1, integer) pieces of character images in descending order of degree of similarity are selected as candidate characters from a character image feature dictionary which stores the image features of character image in units of character, and the first index matrix of M×N cells is prepared. A candidate character string composed of a plurality of candidate characters constituting the first column of the first index matrix, is subjected to a lexical analysis according to a predetermined language model, whereby a second index matrix adjusted into a character string which makes sense is prepared to be utilized for searching.

A document image processing apparatus includes an image capturing unit for capturing an image of a document, a detecting unit for detecting focusing and twisting states of the capture image, a display unit for displaying the detected focusing and twisting states, a character recognition unit for recognizing characters written on the capture image, and a storing unit for storing the recognized characters by fields.

Methods and systems that dynamically control and / or direct document image processing based on one or more of client device display capabilites, image formats supported by the client device, network bandwidth, document file format, document content and user hints.

Embodiments described herein can be used to detect holes in a subset of pixels of a depth image that has been specified as corresponding to a user, and to fill such detected holes. Additionally, embodiments described herein can be used to produce a low resolution version of a subset of pixels that has been specified as corresponding to a user, so that when an image including a representation of the user is displayed, the image respects the shape of the user, yet is not a mirror image of the user. Further, embodiments described herein can be used to identify pixels, of a subset of pixels specified as corresponding to the user, that likely correspond to a floor supporting the user. This enables the removal of the pixels, identified as likely corresponding to the floor, from the subset of pixels specified as corresponding to the user.