Abstract: The disclosure discloses methods and systems for automatically generating multiple scanned files when scanning a document at a multi-function device. The method includes receiving a multi-page document for scanning from a user. A user interface is provided to the user to input one or more keywords and one or more desired resolution values, where the input resolution values are different from a default resolution value set at the multi-function device. A page of the document is scanned to generate a scanned page of a default resolution value. The scanned page is checked if including the one or more input keywords. Accordingly, the default resolution value of the page is converted to the user desired resolution value. The scanning, checking, and converting are repeated till all the pages of the document are scanned. Multiple scanned files of different resolution values are automatically generated from single scan activity.

Abstract: A receipt identification method, an apparatus, a device, and a storage medium are provided. The method includes: obtaining a receipt image; identifying the receipt image by using a region identification model to obtain character regions; utilizing a character identification model to identify the character regions to obtain character contents; and determining receipt information according to the character contents.

Abstract: A system comprising: an input receiving an input document comprising text data and graphical data distinguishing hierarchically first and second portion of the text data; a display displaying said input document; a user interface allowing a user to add, in superposition with the displayed input document, boundary markers visually bounding said first and second text portions; and a processor arranged for, using the boundary markers added to the displayed input document, training a layout data analysis model to determine, in a further input document having further text data, if graphical data distinguishes hierarchically first and second portions of the further text data to display automatically boundary markers visually bounding said first and second portions of said further text data; the user interface allowing said user to correct the boundary markers displayed by the layout analysis model and the processor training the layout data analysis model using the corrected boundary markers.

Abstract: Methods and systems for training a neural network to distinguish between text documents and image documents are described. A corpus of text and image documents is obtained. A page of a text document is scanned by shifting a text window to a plurality of locations. In accordance with a determination that the text in the window at a respective location meets text line criteria, the text in the window is stored as a respective text snippet. A plurality of image windows are superimposed over at least one page of an image document. In accordance with a determination that the content of a respective image window meets image criteria, content of the image window is stored as a respective image snippet. The respective text snippet and the respective image snippet are provided to a classifier.

Abstract: Data processing systems (e.g. image processing systems) and methods are provided for processing a stream of data values (e.g. pixel values). In each of a plurality of iterations, a respective particular data value of the stream is processed by operating on a respective particular subset of data values of the stream. In each iteration: group indication data for at least one group is retrieved and used to define a set of groups into which data values within the particular subset can be grouped; each of the data values within the particular subset is grouped into one of the groups of the set of groups; the particular data value is processed using one or more of the data values of the particular subset in dependence on the classification of the data values into the groups; and group indication data is stored for a group, for use in a subsequent iteration.

Abstract: An image processing apparatus includes a character recognition unit configured to perform character recognition processing for recognizing one or more characters included in image data and acquiring character information, a display unit configured to display one or more characters indicated by the character information acquired by the character recognition unit, and a transmission unit configured to transmit the image data to a folder the name of which is a character selected by a user from among the one or more characters displayed by the display unit.

Abstract: An information processing apparatus includes processing circuitry that acquires an electronic file containing first text data, and determines, based on the acquired electronic file, whether to use the first text data or second text data to perform a process. The second text data is generated through character recognition performed on an image contained in the acquired electronic file.

Abstract: Provided is a sheet processing apparatus which enables processing of a sheet without a decrease in processing efficiency even when the phenomenon that the information cannot be read from the header card arises. The sheet processing apparatus is a sheet processing apparatus that successively processes a plurality of processing-target sheets forming a sheet group, the sheet group including at least one sheet set, the at least one sheet set including a first sheet that is given first recognition information and a second sheet, the sheet processing apparatus includes a recognition unit that reads the first recognition information from one of the plurality of processing-target sheets and a controller that generates second recognition information associated with the one of the plurality of processing-target sheets when the recognition unit fails to read the first recognition information from the one of the plurality of processing-target sheets and a predetermined condition is satisfied.

Abstract: A system and method are capable of ensuring that one or more text strings will be able to be fully rendered in a target area of a user interface or a target area of a graphics file. The system and method determine the number of pixels of first and second reference text that fit in the target area in the horizontal direction and the vertical direction, respectively, determine the number of pixels of string text in the horizontal direction and the vertical direction, and compare the number of pixels in the horizontal direction of the first reference text and the vertical direction of the second reference text respectively to the number of pixels in the horizontal direction and the vertical direction of the text string that is desired to be rendered in the target area to determine whether the text string will fit in the target area.

Abstract: A sheet processing apparatus includes: storage units that each stores therein a sheet with a serial number; a recognition unit that performs first reading processing to read the serial number from the sheet transported from each of the storage units; and a control section that retrieves the serial number having a predetermined relationship relating to a degree of coincidence with the serial number read in the first reading processing, from a serial number list of the sheets stored in the storage units.

Abstract: An image reading apparatus which is capable of preventing occurrence of a paper jam and poor stacking during conveyance of originals. The image reading apparatus sets a type of an original, conveys the original based on the set type of the original, and reads an image on the conveyed original. An original detecting sensor detects placement of the original on an original tray. An LCD touch panel displays an object for setting a type of the original in response to the detection by the original detecting sensor.

Abstract: The disclosed embodiments provide systems and methods for managing a loan application. In one embodiment, a method is disclosed that may include identifying one or more unfulfilled conditions associated with a loan application of a customer and sending, to a customer device, a request for a loan application document based on the identified one or more unfulfilled conditions. The method may also include receiving, from the customer device, a responsive loan application document. The method may also include identifying a document type for the responsive loan application document and confirming that the responsive loan application document is a valid document, Finally, the method may also include sending loan application status information to the customer device based on the confirmation.

Abstract: An information processing apparatus includes a display controller that displays on a display a drawing that expresses a meaning of target data, and an extracting unit that extracts partial data that is at least part of the target data, the partial data being used to express a specific portion if the specific portion is specified as part or whole of the drawing.

Abstract: Disclosed herein is a method and device for identifying bold text in a digital document. The system receives image of digital document which comprises text. The system applies bounding box for each text in the image and scans predefined number of lines in each bounding box to identify width values of pixels. Thereafter, system identifies most occurring width value of pixels among the width values of pixels in each bounding box. The most occurring width value of pixels in each bounding box is identified as box width of corresponding bounding box. The system compares box width of each bounding box with threshold box width. If box width is greater than threshold box width, system identifies text of the bounding box whose box width exceeds threshold box width as bold text. The present disclosure efficiently identifies bold text in digital document based on width values of pixels with less computational power.

Abstract: A compact high frame rate image sensing system has a three CMOS semiconductor circuit chip stack formation, and an imaging method thereof. The bottom chip has an array of light sensitive regions and structures to capture an image. The middle chip includes a Static Random Access Memory (SRAM) or a Dynamic Random Access Memory (DRAM) frame buffer circuit. The top chip includes image processing and logic circuit elements to rapidly extract an image or its main characteristics as determined by a boundary detecting filter block. The image sensing system also includes a compiling tool to provide the programming parameters to the programmable filter blocks in order to optimize the image sensing system for a specific motion detection application.

Abstract: An auto-encoder is configured to verify character detection and/or classification results generated by an automated optical character recognition system. The auto-encoder may be trained to reconstruct visual representations of the detected character, and a determination of whether the character detection result comprises a true positive or false positive may be based on a reconstruction error between the image data in which the character was detected and a reconstructed image generated by the auto-encoder.

Abstract: A method and apparatus for recognizing a character area in an image are provided. A specific embodiment of the method comprises: acquiring color values and position information of pixel points in a to-be-recognized image; clustering the pixel points based on the color values of the pixel points, the color values of the pixel points in each pixel point category being identical or similar; determining, for each category of clustered pixel points, outlines of connected regions including the pixel points in each category of pixel points, to obtain an outline set; and merging, based on the color values and the position information of the outlines in the outline set, the outlines, to obtain character areas in the image. The embodiment has improved the accuracy of recognizing character lines in recognizing characters in an image.

Abstract: Systems and methods for generating high resolution dewarped images for an image of a document captured by a 3D stereo digital camera system, or a mobile phone camera capturing a sequence of images, which may improve OCR performance. Example embodiments include a compact stereo camera with two sensors mounted at fixed locations, and a multi-resolution pipeline to process and to dewarp the images using a three dimensional surface model based on curve profiles of the computed depth map. Example embodiments also include a mobile phone including a camera which captures a sequence of images, and a processor which computes a disparity map using the captured sequence of image frames, computes a model of the at least one document page by generating a cylindrical three dimensional geometric surface using the computed disparity map, and renders a dewarped image from the computed model.

Abstract: According to one embodiment, an image processing apparatus includes an image reading device, a storage device, and a control unit. The image reading device reads an image on a sheet. The storage device stores information. The control unit that determines a detection area of an encoded image based on a teacher image which is an image read from a predetermined teacher sheet by the image reading device, records information indicating the detection area in the storage device, detects an encoded image in the detection area among the images read from a sheet to be read after the teacher sheet, and decodes the detected encoded image.

Abstract: In an image forming apparatus, a processor acquires target image data representing a target image. The processor identifies as a first type pixel in the target image, and sets a target pixel from among peripheral pixels of the pixel identified as the first type pixel. The processor identifies the target pixel as a second type pixel in a case where the target pixel satisfies a specific condition. The processor generates processed image data by performing a replacement process in which a pixel value of the pixel identified as the first type pixel is replaced with a first value representing a first color and a pixel value of the pixel identified as the second type pixel is replaced with a second value representing a second color. The specific condition includes a condition that all specific pixels in a specific range match a specific pattern.

Abstract: Rights holders such as copyright owners want to keep track of copying of printed materials owned by them. That information can be used to check if the person copying has a license. Alternatively, the information can be used for billing. In some countries, an intermediary such as a copyright agency may facilitate the tracking of such copying and the compensation of the rights holders. This system automates the process by monitoring copiers, matching copied images to materials owned by rights holders, and recording such copying actions including the identifier of the copier, the copying person, the number of copies, and the matched materials. Alternatively, the system may prevent the copying if there is no permission by the rights holders.

Abstract: An image processing unit includes a region separation device and a spatial filtering device. The region separation device detects line widths of a manuscript image in which the line widths are different between a vertical line and a horizontal line and determines which of the vertical line or the horizontal line is thinner. The spatial filtering device executes an emphasizing process to make a widening ratio of a thinner line of the vertical line or the horizontal line higher than a widening ratio of the other line.

Abstract: A method of modified SAO (sample-adaptive offset) processing for a reconstructed picture in a video coding system to improve the performance is disclosed. In one example, a SAO-sign threshold is introduced to determine the sign of the difference between a current reconstructed pixel and a neighboring reconstructed pixel. A range of difference values greater than the negative SAO-sign threshold and smaller than the positive SAO-sign threshold is assigned to have a sign value of 0. In another example, the SAO-offset value is derived by multiplying the SAO-offset sign with a result from applying left shift by the SAO-bit-shift value to the absolute SAO-offset value. In yet another example, the absolute SAO-offset value is coded by truncated Rice (TR) codes and a maximum TR value is indicated by a syntax element.

Abstract: Described herein are an apparatus, method, and computer-readable medium. The apparatus including processing circuitry configured to extract a textual content included within a digital document, perform a text search using the extracted textual content on an indexed master document database to identify one or more master documents that are similar, within a pre-determined threshold, to the digital document, generate a candidate master document list using the one or more master documents identified based on the text search, extract a plurality of features of the digital document, perform a comparison, after performing the text search, of the plurality of features of the digital document with features of the one or more master documents in the candidate master document, and identify a master document of the one or more master documents that matches the digital document based on the comparison of the features.

Abstract: A copy method used in a copy system or a copy apparatus connected to a cloud server includes steps of: scanning a document to obtain old image data containing an old information block; generating new image data containing a new information block according to the old image data; printing the new image data on a medium; and comparing different generations of original image data, one of which is contained in the old image data, in the cloud server to judge whether improper modifications are present on the original image data or not, and notifying an information office to perform an inspection when the improper modifications are present.

Abstract: An image processing apparatus includes: an extractor that divides image data in block units and extracts a maximum value and a minimum value of each block from the compressed image data; an edge detector that detects an edge at a front end or a rear end of an image; a correction value calculator that corrects the maximum value, or the maximum value and the minimum value of each block positioned in a certain range from the front end or the rear end and calculates a maximum value and a minimum value after the correction; and a converter that determines a conversion formula of a pixel value by using the maximum value and the minimum value before the correction and the maximum value and the minimum value after the correction and converts each pixel value of the image data obtained by decompressing the compressed data so as to apply sweeping correction.

Abstract: A continuous reading mode is a mode in which reading of a document placed on a contact glass is continued and a job is started after completion of reading is accepted. In reading of the second and subsequent sheets of the document in a set reading range, a reading controller does not move the position of the reading line of an image sensor to outside the end position of the reading range in the sub-scanning direction as seen from a home position.

Abstract: Introduced here is a technique to create small compressed image files while preserving data quality upon decompression. Upon receiving an uncompressed data, such as an image, a video, an audio, and/or a structured data, a machine learning model identifies an object in the uncompressed data such as a house, a dog, a text, a distinct audio signal, a unique data pattern, etc. The identified object is compressed using a compression treatment optimized for the identified object. The identified object, either before or after the compression, is removed from the uncompressed data. The uncompressed data with the identified object removed is compressed using a standard compression treatment.

Abstract: A method for processing a stroke in an image is provided. The stroke includes a plurality of pixels and the method includes: executing a modified 4-way stroke width transform (SWT) on a mask of the stroke; determining a plurality of certain centerline points among the pixels based on the modified SWT; generating a plurality of polylines within the stroke based on the certain centerline points; determining a plurality of regions of certainty based on the polylines; removing the regions of certainty from the mask and leaving a plurality of regions of uncertainty in the mask; calculating a plurality of joints and end caps for each of the polylines based on the polylines and the regions of uncertainty; generating a completed polyline path by connecting the polylines based on the joints and end caps; and generating a description of the stroke based on the completed polyline path.

Abstract: A method and a system are described for performing optical character recognition on an image including a plurality of printed characters. The method includes defining one or more opcodes and direction pointers associated with the plurality of printed characters of a language and a font type, wherein each of the one or more opcodes has an associated unique opcode characterization value. The method includes creating a binary tree comprising a plurality of nodes, wherein each node of the plurality of nodes is assigned the unique opcode characterization value. The method includes retrieving a set of operations associated with the unique opcode characterization value assigned to each of the plurality of nodes. The method includes navigating the binary tree from a root node to a leaf node based on the set of operations, the first pointer value, and the second pointer value until the leaf node is reached.

Abstract: Provided is an image forming apparatus including a charge processing section and an operation section that are brought closer in height to each other, thus improving the operability of a user. An image forming apparatus (100) includes a coin insertion processing section (110), an operation panel (120) and an electrophotography printer (130). The coin insertion processing section (110) is configured to accept money and then execute charge processing so as to permit image formation by the image forming apparatus (100). The operation panel (120) is configured to, when the coin insertion processing section (110) executes the charge processing, accept setting of image formation by the image forming apparatus (100). The electrophotography printer (130) is configured to form an image of the read image data based on setting at the operation panel (120). The coin insertion processing section (110) is disposed at a height equal to a height of the operation panel (120).

Abstract: Systems and methods are provided for quickly and efficiently searching and receiving results for real estate-related information without or at least with minimal human processing of real estate-related documents. Optical character recognition on a plurality of scanned document images is performed to obtain a plurality of textual data representations of the real estate-related documents. Data is extracted from the textual data representations, and subsequently contextualized according to a real estate-related context. Aspects of the extracted data as well as the textual data representations are provided as search results based on one or more searches for real estate-related information.

Abstract: A system and method for characterizing the sensitivity of image data to compression. After a video signal is transformed to the frequency domain, statistical data regarding a video signal or frame of a video signal can be calculated. In one alternate, a contour map of the original signal can be calculated and the parameters of the contour map can be recorded. The same signal can be compressed and then upscaled and a second contour map can be calculated and the parameters of the second contour map can be recorded. Based on the difference between the first and second contour maps, a sensitivity of the video to compression can be determined.

Abstract: An image processing apparatus includes an image processing device. The image processing device includes a receiving port and a processor connected together. The receiving port receives old image data corresponding to a document image of a document. The processor divides the old image data into first area image data corresponding to a first area image of the document, and second area image data corresponding to a second area image of the document, and further performs image enhancement processing on the first area image data to obtain enhanced first area image data. Thus, the first area image may be separated from the second area image, and the image enhancement processing is performed on the first area image. The enhanced first area image data and the second area image data are separately outputted or combined for output.

Abstract: An example method is of image processing provided in according with one implementation of the present disclosure. The method includes receiving an image, placing a window across the image, and computing a set of all occurring grayscale values within the window. The method further includes computing a threshold value based on the set of all occurring grayscale values within the window and determining an output pixel value of at least one pixel from the window based on the threshold value.

Abstract: An image processing apparatus processes a first image signal including pixel signals, the first image signal having a picture portion in which a subject is shown and having a blank portion surrounding the picture portion. The apparatus includes: a blank detection unit configured to set similar frames different in size from one another within a display area of a screen representing the first image signal, in a stepwise manner from an outer periphery, and to detect the blank portion based on whether or not a part of the pixel signals belonging to a region outside each of the similar frames has the uniform color or brightness; a region-of-interest setting unit configured to set an initial region-of-interest corresponding to the picture portion in the first image signal, based on the blank portion; and a region-of-interest image generation unit configured to generate a region-of-interest image signal representing the initial region-of-interest.

Abstract: An image processing apparatus includes an exaggeration unit configured to perform on an original image including a hand-drawn element an exaggeration process that expands the hand-drawn element to generate an exaggerated image; and a reduction unit configured to reduce the exaggerated image to generate a reduced image of a predetermined size smaller than a size of the original image.

Abstract: A display panel driver includes a scaler circuit performing image enlargement processing on input image data corresponding to an input image to generate ?-times enlarged image data corresponding to an ?-times enlarged image (? is a number larger than one which cannot be represented as 2k); and a driver section driving a display panel. In calculating a pixel value of a target pixel of the ?-times enlarged image, the scaler circuit generates enlarged image data including 2n-times enlarged image data corresponding to a 2n-times enlarged image obtained by enlarging the input image with an enlargement factor of 2n (n is the smallest integer determined so that 2n is larger than ?), and calculates the pixel value of the target pixel from the 2n-times enlarged image data through interpolation processing of pixel values of pixels of the 2n-times enlarged image corresponding to the target pixel of the ?-times enlarged image.

Abstract: An image processing apparatus includes an image reading unit, a character recognition unit, an operation unit, and a file generation unit. The image reading unit generates image information which includes at least one of a character string and a table. The character recognition unit recognizes characters and generates character information corresponding to each character included in one of the at least one of the character string and the table. The operation unit receives, from a user, a selected file format of an electronic file to be generated. The file generation unit generates an electronic file including the generated character information in accordance with the selected file format. The character recognition unit recognizes the characters and generates the character information in the generated image information in accordance with the one of the at least one of the character string and the table that corresponds to the selected file format.

Abstract: The present invention discloses methods and systems for recognizing an object in an input image based on stored training images. An object recognition system the input image, computes a signature of the input image, compares the signature with one or more stored signatures and retrieves one or more matching images from the set of training images. The matching images are then displayed to the user for further action.

Abstract: Methods and apparatus are provided for identifying optimal threshold values to generate optimal binary images from a digital image. In one example, a method includes, for each of a plurality of candidate threshold values, processing an image using the candidate threshold value to create a first segmented image of a first plurality of blobs; for each of the plurality of candidate threshold values, calculating a threshold value evaluation metric as a count of qualifying blobs in the first plurality of blobs in the first segmented image, wherein the qualifying blobs have a fill factor exceeding a predefined fill factor and have an area within a predefined area range; identifying an optimal threshold value from the plurality of candidate threshold values for which the threshold value evaluation metric is maximized; and processing the image using the optimal threshold value to create a second segmented image of a second plurality of blobs.

Abstract: Dynamically-generated images sized according to a requesting web client application display resolution are provided. The client application may calculate a target display resolution and pass the target display resolution as an input parameter with a request to a server for application content. The server may use the desired size input parameter to determine an optimal image size for the target display resolution. The server may render the application content as one or more images to the optimal image size and send the rendered image(s) to the client application. A determination may be made by the client application to display the image(s) at the size received or to scale the server-provided image(s). If the available area in the client application pane changes, the client application may recalculate the target display resolution and issue a new request to the server with the new target display resolution as the desired size input parameter.

Abstract: Implementations generally relate to data-charge phase data compression. In one implementation, a method includes computing prediction values for image data, where the image data is data-charge phase data, and where the computing of prediction values is based on inter-block prediction. The method also includes computing residual data based on the prediction values. The method also includes quantizing the residual data. The method also includes entropy encoding the quantized residual data. The method also includes refining an inverse quantized residual data based on one or more of the residual data and a number of left-over bit-budget after entropy encoding.

Abstract: An integrated circuit includes a pixel identifying unit that extracts a target partial image formed of a pixel of interest and adjacent pixels from input image data, determines a character of the pixel of interest based on the pixel of interest and the adjacent pixels, and generates identification information indicating a result of determination on the character; and a density converting unit that converts a density of a pixel of the image data based on a contour extraction function or an edge density reducing function on the image data by using the identification information.

Abstract: Provided is an analysis target region setting apparatus that can accurately set an analysis target region, based on an observation image of a sample obtained with an optical microscope and the like irrespective of texture on the sample surface when the analysis target region is set therein. The analysis target region setting apparatus according to the present invention divides the observation image into a plurality of sub-regions based on pixel information on each pixel constituting the observation image. Subsequently, consolidation information on each sub-region is calculated, and two adjacent sub-regions themselves are consolidated based on the consolidation information. According to this, it is possible to divide the observation image into sub-regions having similar pixel information with a disregard of noise attributed to the shape of a surface and the like. A user designates one sub-region from among the sub-regions finally obtained, as the analysis target region.

Abstract: Embodiments digitize radiology films into DICOM format. Radiology films typically include an array of captured images laid out in a grid pattern. To comply with DICOM format, the scanned image of a radiology film is segmented into sub-images and text is extracted from the sub-images to generate DICOM metadata. The sub-images and extracted text metadata are then combined to generate a DICOM-compliant multi-image file.

Abstract: An image compressing device includes: a histogram creating unit configured to create a histogram regarding an input image; an original type recognizing unit configured to recognize an original type of the input image using the histogram; and an image compressing unit configured to perform a compression process for creating a high-compressed image file from the input image and to control a compression mode of the compression process depending on at least the original type recognized by the original type recognizing unit.

Abstract: An image reading apparatus includes an image reading section and a detection section. The image reading section includes at least two detection units, and performs a reading operation on an image. The at least two detection units have respective spectral characteristics which are different from each other. The detection section detects a condition of an irregularity on an image carrier by comparing a detection result of the image read by the image reading section with an output characteristic. The output characteristic is stored in advance and is a color component obtained from a value obtained by the image reading section reading a test image having a region in at least one color.

Abstract: An electronic image in a first color space, used by image acquisition devices, is obtained and converted into a second color space with a larger gamut, to produce a second color space image. Corrections are made to the second color space image to produce a corrected image, without performing background suppression. The corrected image is converted into a third color space, used by printing devices, to produce a third color space image, and this process of converting the corrected image into the third color space includes performing background suppression. This process of converting the corrected image into the third color space samples nodes of the second color space values, classifies the nodes as background nodes or non-background nodes, multiplies the second color space values of the background nodes by a percentage less than 100%, and after multiplying, interpolates values between the nodes.

Abstract: When an upper layer of a device is going to initiate an exchange of two or more messages with a corresponding upper layer of another device, the initiating device will provide from its upper layer to a lower layer such as a MAC layer an indication of how many messages the devices will be exchanging. In response to that indication, the lower layer of the initiating device will then cause the lower layer of the other device to forgo checking for and confirming availability of the channel for transmission of the next message of the exchange from the other device to the initiating device. Further, the lower layer of the initiating device may also responsively forgo for and confirming availability of the channel for a subsequent message of the exchange.