Abstract: Methods and apparatus for training neural networks to identify information table partitions are described. Also described are methods and apparatus of using a trained neural network to process an image and provide partition information in an easy to use format. The format of the partition information is one which is simple to interpret, easy to communicate and uses values which facilitate successful training and recognition of partitions in tables whether the partitions be implicitly defined by data arrangement or explicitly define using lines. An image is treated as including a predetermined number of row and column portions. The neural network generates for each predetermined portion a partition present indicator value and a partition location value. The partition present value in some embodiments is a value in the range of 0 to 1 and the partition location value in some embodiments is a value in the range of ?1 to +1.

Abstract: Methods and apparatus for converting an OOXML file into a format which can be rendered, displayed and edited by a browser on a device such as a cell phone without the device having to directly work with the document in the OOXML format are described. In various embodiments the contents of an OOXML file are converted into a JSON object, communicated to a client device which can display and edit the document contents. A revised version of the JSON object including edits is returned and converted back into an OOXML file. The method allows for preserving document format and other information while avoiding the need for a client device to support display and direct editing of a document in OOXML format.

Abstract: Methods and apparatus for extracting information corresponding to a user selected area of a displayed web page are described. A user selected region, e.g., rectangular region, of a displayed web page is identified based on received user input. The elements beneath the user selected region are converted to a raster data URL. An HTML5 image element is created with an src attribute set to the raster data URL and with a low image element opacity property. The created HTML5 image element is added to the web page as an overlay. The web browser's built-in copying functionality can now be used to copy the overlying image element to the clipboard as an image as desired, e.g., using a context menu which enables image MIME type data to be placed on the clipboard.

Abstract: Various features relate to processing a scanned image to facilitate accurate locator pattern identification and/or detection of the corner locations of the locator pattern. In some embodiments to facilitate the identification of corner points the scanned image is processed to reduce the effect of noise and/or other damage on the subsequent location identification process. Individual white pixels which have black pixels on four sides are converted to black as part of the processing while multiple white pixels adjacent each other are left unaltered. In some embodiments processing does not alter the color of black pixels. Corner points of the locator pattern are identified through additional processing and identification of line segments satisfying an expected black, white, black, white, black segment portion ratio.

Abstract: Methods and apparatus relating to the transfer of data for processing and/or the transfer of the resulting processed data are described. Some features relate to a processing system which performs data transfers under control of a Dynamic Sequence Controller (DSC). In various embodiments a sequence of operational codes is used to control data transfer with the status of data source and destination locations taken into consideration. Modification of the op code sequence used to control the dynamic sequence controller and thus the transfer of data can be performed asynchronously to control of processing units which can be controlled via a command and control bus used to control the function of operators which process the data provided via the data bus.

Abstract: An input SVG file to be processed is accessed. Reusable symbols in the input SVG are identified, e.g., which satisfy a symbol size requirement. A set of symbols are selected from among the identified reusable symbols for conversion to glyphs of a custom binary font, e.g., based on symbol occurrence frequency. A binary font file is created corresponding to set the selected identified symbols in the SVG input file. An SVG output file is created including: binary font glyph definitions corresponding to the converted identified symbols, definitions of symbols from the SVG input file which have not been converted to glyphs and information indicating where the glyphs and symbols, which were not converted, are to be placed on an output display page. The generated SVG output file is a more efficient SVG file than the input SVG file. Different custom binary font files are created for different SVG input pages.

Abstract: Methods and apparatus for managing resource utilization in a distributed system are described. Devices, e.g., servers, which use resources, e.g., processing cores, act as individual policy enforcement points. Individual servers retrieve and maintain local copies of resource lease records which are stored in a centralized data storage system. The individual server compares locally stored lease records to the retrieved lease records to check for any tampering in the centralized data storage and multiple states are supported to take into consideration transitory conditions and/or communications delays. Verification states include, e.g., a Pending Active state and a Pending Inactive State, in addition to an Active state and Inactive state, to delay licensing enforcement to account for centralized storage system eventual consistency delays.

Abstract: Image binarization methods and apparatus are described. A set of input image pixel values, e.g., a set of grayscale values corresponding to an input image, is processed to determine whether to recommend to use local binarization thresholds or a global binarization threshold. Edges including edge pixels are identified. A first histogram corresponding to edge pixel values and a second histogram corresponding to image pixel values are generated, subjected to one or more smoothing operations, and truncated, based on information derived from the edge histogram. Characteristics of the histograms including, e.g., minima, maxima, points of inflection, and hidden peaks, are determined, evaluated, and used to decide between local binarization thresholds and a global threshold. Based on the recommendation, a global threshold is used or local thresholds are used to process the set of input image pixel values and generate a corresponding set of bi-level values.

Abstract: Methods and apparatus for: identifying perimeter lines in an image, e.g., document border lines forming a non-rectangular quadrilateral corresponding to a scanned document, determining document corner points, and correcting the input image based on determined corner points are described. Lines are identified in the input image and a line weight is generated for each identified line. The identified lines are classified into two different groups based on direction, e.g., predominately vertical or predominately horizontal. For each group at least two, and sometimes more, candidate perimeter lines are determined to be kept, based on line weight and line length, and other lines in the group are eliminated. Two best candidate perimeter lines are identified from each group, e.g., based on distance between the remaining lines in the group. Four document corner points are determined based on the remaining lines in the two groups.

Abstract: Methods and apparatus for generating a binarization threshold are described. A set of input image pixels is processed. Edges including edge pixels are identified. In various embodiments histograms of pixel values and edge pixel values are generated and jointly used in determining an appropriate binarization threshold. In some embodiments a first histogram of edge pixel values is used to determine an interval of pixel values of interest to limit the set of pixel values used for determining a binarization threshold statistically. In some embodiments a first histogram corresponding to edge pixel values and a second histogram corresponding to image pixel values are generated, subjected to one or more smoothing operations, and truncated, based on information derived from the edge histogram. Characteristics of the histograms including, e.g., minima, maxima, are determined, evaluated, and used to generate a best global threshold.

Abstract: Methods and apparatus for detecting labels included in a document or other binarized image, and for extracting and/or using information associated with a label, are described. A nodal structure modeling objects, e.g., characters, character strings or words, which make up various label aliases are described. The nodal structure is used to generate a score for portions of a binarized document with the scores being used to determine the presence or absence of one or more label aliases. When a label alias is determined to be present, information is extracted from the document and used as information corresponding to a label to which the identified label alias corresponds. Multiple different label aliases may correspond to a single label allowing multiple different aliases to be used to identify the same information. The label aliases and information extraction can be and sometimes used to extract information from scanned forms.

Abstract: Methods and apparatus for identifying lines in an image are described. An image to be processed is divided into a plurality of tiles, and processing is performed on a per tile basis. Lines are identified in tiles and a weight is assigned to each line based on among other things, the length of the line. Quantized first and second parameter values, e.g., values defining where lines enters and leave an area, are used in defining the identified lines. A set of lines is selected based on the weight information and output or used in image processing the image including the lines.

Abstract: Bi-level pixel values are generated from a set of input pixel values corresponding to an image. Various described methods and apparatus are well suited for applications with limited computational capability and/or limited available resources to be used for performing image processing. Corresponding to an individual input pixel being processed, a plurality of windows including the pixel are evaluated to determine statistics including a variance for each window. Based upon the determined variances, one of a plurality of binarization threshold generation functions is selected. A binarization threshold for the input pixel is determined using the selected binarization threshold generation function. A bi-level pixel value is generated based on a comparison of the input pixel value to the generated binarization threshold.

Abstract: Methods and apparatus for coding and/or decoding bitplanes of individual codeblocks are described. Aspects relate to speeding up bitplane decoding when one or more decoders are used as part of the decoding process and one or more consistent value bitplanes were coded at the start of a codeblock. A number F, e.g., of consistent value, e.g., zero value, bitplanes are identified as corresponding to the beginning of an encoded codeblock being processed. Based on the determination a predetermined output, e.g., zero values corresponding to F bitplanes, is output. Thus, the output corresponding to the F consistent value bitplanes can be produced without having to perform a full arithmetic decoding process to generate the decoded data corresponding to the F consistent value bitplanes. Remaining bitplanes of a codeblock including data are subjected to decoding using one or more decoder modules which maybe part of a JPEG 2000 compliant decoder.

Abstract: Methods and apparatus for coding and/or decoding bitplanes are described. Aspects relate to speeding up bitplane coding when one or more entropy coders are used as part of the encoding process. A number, e.g., three, consistent value, e.g., zero value, bitplanes are identified and subjected to coding, e.g., in some embodiments using a JPEG 2000 arithmetic coder. Remaining bitplanes including data are subjected to coding using a second coding process, e.g., an entropy coding process implemented by a JPEG 2000 selective arithmetic bypass coder. By subjecting zero value bitplanes to the coding, e.g., arithmetic coder processing or its equivalent, 3 bitplanes are subjected to fast, easy to implement coding while non-consistent value bitplanes can be coded using selective arithmetic bypass coding. This satisfies the JPEG 2000 requirement that 3 bitplanes be generated in accordance with arithmetic coder processing while avoiding the normal delays associated with processing of non-consistent value bitplanes.

Abstract: Methods and apparatus for detecting the presence and location of punch holes in a scanned image are described. The punch hole detection methods and apparatus rely at least in some embodiments on whether a portion of the scanned image, referred to as a component, corresponds to a punch hole by comparing one or more characteristics of the component such as its circularity, aspect ratio, black to white pixel ratio, density, height and/or width to one or more thresholds before making a decision as to whether or not the component is a punch hole. In some embodiments the components which pass component-level checks are grouped and one or more group-level checks are performed on the components to determine if the components are punch holes. Once a punch hole is detected, in some embodiments, the image is processed to remove the detected punch hole.

Abstract: Methods and apparatus for processing one or more images, e.g., images representing pages including text, to detect and in some instances correct the orientation of the page. In some embodiments the methods and apparatus for processing image data comprise generating a histogram of foreground pixel counts corresponding to a current line of text of the image being processed with the foreground pixel counts corresponding to different rows of pixels corresponding to the current line of text and identifying based on statistical analysis of the generated histogram whether the current page of text is oriented in an inverted or non-inverted position. In some embodiments analysis is performed on multiple lines of text with cumulative statistics being used in to determine the orientation of the page. In some embodiments, a page whose orientation is determined to be upside down is re-oriented to be right-side up.

Abstract: To facilitate rendering an image, e.g., a portion of a PDF page, at higher resolutions or locations than could be expressed using standard 32 bit fixed point integer values, an image is segmented and a user space coordinate system origin used for individual segment processing is transformed on a per segment basis to each segment locality before a render request is made to a rendering function library. After a new origin of a segment is established, the PDF page content contained within that locality corresponding to the individual segment being processed is rendered, e.g., using functions available in the PDF software library. The results of processing the segments is combined to produce a final high-resolution image. While the input to the rendering process may include values which can not be expressed in 32 bit fixed point notation, the segmentation process allows the individual segments to be rendered using rendering specified using such notation.

Abstract: Methods and apparatus for efficiently locating QR code finder patterns and/or code QR alignment patterns in an image are described.

Abstract: Microsoft's recently proposed new image compression codec JPEG XR is currently undergoing ISO standardization as JPEG-XR. Even though performance measurements carried out by the JPEG committee indicated that the PSNR performance of JPEG XR is competitive, the visual performance of JPEG XR showed notable deficits, both in subjective and objective tests. This paper introduces various techniques that improve the visual performance of JPEG XR without leaving the current codestream definition. Objective measurements performed by the author indicate that the modified encoder, while staying backwards compatible to the current standard proposition, improves visual performance significantly, and the performance of the modified encoder is similar to JPEG.