An information processing system includes circuitry. The circuitry acquires a captured image by capturing a document. The circuitry performs an analysis process using the captured image. The circuitry selects, for each of at least one setting item of a plurality of setting items relating to image processing to be performed on the captured image, at least one setting value from among configurable setting values as a candidate for a recommended setting. The circuitry performs image processing repeatedly on the captured image while changing setting values of the plurality of setting items with a setting value of the at least one setting item restricted to the at least one setting value selected as the candidate for the recommended setting. The circuitry determines recommended settings for the plurality of setting items relating to image processing to obtain an image suitable for character recognition.

An information processing system includes circuitry. The circuitry acquires a captured image by capturing a document. The circuitry performs an analysis process using the captured image. The circuitry selects, for each of at least one setting item of a plurality of setting items relating to image processing to be performed on the captured image, at least one setting value from among configurable setting values as a candidate for a recommended setting. The circuitry performs image processing repeatedly on the captured image while changing setting values of the plurality of setting items with a setting value of the at least one setting item restricted to the at least one setting value selected as the candidate for the recommended setting. The circuitry determines recommended settings for the plurality of setting items relating to image processing to obtain an image suitable for character recognition.

A method and apparatus for extraction of dots in an image are described. An image is binarized according to an initial intensity threshold to obtain an initial binary image including foreground and background pixels. Each foreground pixel has a foreground intensity value and each background pixel has a background intensity value. A set of blobs including foreground pixels is selected from the initial binary image to be part of a selected set of dots, where each blob from the set of blobs has characteristics of a dot. Responsive to determining that a successive binarization is to be performed, the following operations are repeated: (1) binarization of the image according to a successive intensity threshold (2) selection of a successive set of blobs, where each blob has characteristics of a dot. Responsive to determining that a successive binarization is not to be performed, the selected set of dots is output.

A computer-implemented method, according to one embodiment, includes using a trained semantic consistency model to determine a semantic consistency of contents of two screenshots. The trained semantic consistency model bases the semantic consistency on dimensions including: a linguistic comparison of the contents, an image comparison of the contents and a text location comparison of the contents. The method further includes outputting the determined semantic consistency for display on a user device. A computer program product, according to another embodiment, includes a computer readable storage medium having program instructions embodied therewith. The program instructions are readable and/or executable by a computer to cause the computer to perform the foregoing method. A system, according to another embodiment, includes a processor, and logic integrated with the processor, executable by the processor, or integrated with and executable by the processor. The logic is configured to perform the foregoing method.

A computer-implemented method, according to one embodiment, includes using a trained semantic consistency model to determine a semantic consistency of contents of two screenshots. The trained semantic consistency model bases the semantic consistency on dimensions including: a linguistic comparison of the contents, an image comparison of the contents and a text location comparison of the contents. The method further includes outputting the determined semantic consistency for display on a user device. A computer program product, according to another embodiment, includes a computer readable storage medium having program instructions embodied therewith. The program instructions are readable and/or executable by a computer to cause the computer to perform the foregoing method. A system, according to another embodiment, includes a processor, and logic integrated with the processor, executable by the processor, or integrated with and executable by the processor. The logic is configured to perform the foregoing method.

There is provided an image processing apparatus in which a part used in predetermined processing is specified with use of a relatively small binarization threshold, from parts that have been converted into black pixels through binarization processing using a relatively large binarization threshold.

A portable writing apparatus includes a writing instrument carriage to hold a writing instrument and an actuator system coupled to the writing instrument carriage to move the writing instrument carriage. A controller is electrically coupled to the actuator system, and the controller includes logic that when executed by the controller causes the controller to perform operations including: receiving input data including a user's handwritten characters; and controlling the actuator system to move the writing instrument carriage in response to the input data. The writing instrument carriage traces a shape of the user's handwritten characters.

A structured data processing system includes hardware processors and a memory in communication with the hardware processors. The memory stores a data structure and an execution environment. The data structure includes an electronic document. The execution environment includes a data extraction solver configured to perform operations including identifying a particular page of the electronic document; performing an optical character recognition (OCR) on the page to determine a plurality of alphanumeric text strings on the page; determining a type of the page; determining a layout of the page; determining at least one table on the page based at least in part on the determined type of the page and the determined layout of the page; and extracting a plurality of data from the determined table on the page. The execution environment also includes a user interface module that generates a user interface that renders graphical representations of the extracted data; and a transmission module that transmits data that represents the graphical representations.

A method for analyzing a PDF document includes: modifying, by an analyzer, a background color of the document to a second color to generate a modified document; converting, by a noise removal module (NRM), the modified document into an image; making, by the NRM, a first determination that the image comprises a background noise, in which the noise is reduced by modifying an area within the image; generating, by a fraud detection module (FDM), at least one image patch from the image; generating, by the FDM, an embedding for the at least one image patch, in which the embedding is processed using a convolutional neural network (CNN) layer; making, by the FDM and based on an output of the CNN layer, a second determination that the document is invalid; and notifying, by the FDM, a user about the second determination using a GUI of the client.

A method for analyzing a PDF document includes: modifying, by an analyzer, a background color of the document to a second color to generate a modified document; converting, by a noise removal module (NRM), the modified document into an image; making, by the NRM, a first determination that the image comprises a background noise, in which the noise is reduced by modifying an area within the image; generating, by a fraud detection module (FDM), at least one image patch from the image; generating, by the FDM, an embedding for the at least one image patch, in which the embedding is processed using a convolutional neural network (CNN) layer; making, by the FDM and based on an output of the CNN layer, a second determination that the document is invalid; and notifying, by the FDM, a user about the second determination using a GUI of the client.