Abstract: Provided is a model generation system for generating a text line recognition model that recognizes a text line included in a text line image, the model generation system including a processor section, in which the text line recognition model includes a visual feature extractor and a language context relation network, the processor section determines a variable of the language context relation network by acquiring text data for training and thus training the language context relation network by using the acquired text data, determines a variable of the visual feature extractor by training the text line recognition model through the use of a labeled text line image while the variable of the language context relation network is fixed, and generates the text line recognition model while the variable of the language context relation network is set to the determined variable thereof and the variable of the visual feature extractor is set to the determined variable thereof.

Abstract: Provided is a model generation system for generating a text line recognition model that recognizes a text line included in a text line image, the model generation system including a processor section, in which the text line recognition model includes a visual feature extractor and a language context relation network, the processor section determines a variable of the language context relation network by acquiring text data for training and thus training the language context relation network by using the acquired text data, determines a variable of the visual feature extractor by training the text line recognition model through the use of a labeled text line image while the variable of the language context relation network is fixed, and generates the text line recognition model while the variable of the language context relation network is set to the determined variable thereof and the variable of the visual feature extractor is set to the determined variable thereof.

Abstract: A system trains a machine learning model which recognizes characters of text images. The system stores the machine learning model which recognizes characters of text images. The machine learning model includes a character segmentation network which is configured to extract visual features from text images, and to generate character bounding boxes from the text images, a domain adaptation network configured to classify the text images into domains based on the visual features, and a text recognition network configured to recognize characters in the text images based on the character bounding boxes and the visual features. The system is configured to (1) reverse gradients in the training of the domain adaptation network to minus gradients and back-propagate the minus gradients through the character segmentation network (2) back-propagate gradients in the training of the text recognition network through the character segmentation network.

Abstract: A personal information separation unit separates a document image containing personal information into a personal information image containing the personal information and a general information image that does not contain the personal information on the basis of the document image, and transmits the general information image to a cloud server. A recognition result integration unit receives a general recognition result that is the recognition result of the character recognition processing for the general information image from the cloud server, and acquires a target recognition result that is the recognition result of the character recognition processing for the document image in accordance with the general recognition result and the information based on the personal information image.

Abstract: A character recognition system converting image data of a character string into a character code is provided, which includes a data processing unit, and a storage unit configured to be used by the data processing unit, wherein the storage unit stores similar-outline nonsense character string data that has an outline similar to that of to an ordinary character string but does not make sense, and the data processing unit performs character recognition processing using the similar-outline nonsense character string data that is stored in the storage unit.

Abstract: A computing machine managing a template manages a document format, a template, and a cluster generated on the basis of a classification result based on a position of the document in a feature space in such a manner that they correspond to one another; determines whether a cluster to which a target document can belong is present on the basis of a position, in the feature space, of the target document in a case of detecting an opportunity of generating a template of the target document; registers the template of the target document in a case of determining that the cluster to which the target document can belong is not present; generates a cluster corresponding to the registered template; and manages a document format of the target document, the registered template, and the generated cluster in such a manner that they correspond to one another.

Abstract: An information processing apparatus which performs table recognition on an input image including a joined table area including different table areas joined performs character recognition processing on at least the joined table area of the input image, extracts an item name from a character string obtained as a result of the character recognition processing, and recognizes, when detecting, in a column or a row having one item name as a starting point in the joined table area, an item name different from the one item name at a position advanced in one direction, an area that extends from the different item name as a different table area.

Abstract: A personal information separation unit separates a document image containing personal information into a personal information image containing the personal information and a general information image that does not contain the personal information on the basis of the document image, and transmits the general information image to a cloud server. A recognition result integration unit receives a general recognition result that is the recognition result of the character recognition processing for the general information image from the cloud server, and acquires a target recognition result that is the recognition result of the character recognition processing for the document image in accordance with the general recognition result and the information based on the personal information image.

Abstract: A computer that extracts an attribute which is a text string contained in an predetermined examination target document stores template information for managing a plurality of templates in which a type of attribute is defined, executes a text recognition process on image data of the document, extracts an attribute corresponding to the type of attribute using a result of the text recognition process and the plurality of templates, selects a template based on the extracted attribute, generates output information that includes the attribute extracted using the selected template and is used for the examination; determines a type of confirmation operation performed on the output information, before the examination, based on a comparison result between an evaluation value indicating credibility of the output information and a threshold, and corrects the determined type of confirmation operation based on the text string contained in the document.

Abstract: A computer, which is configured to generate learning data for use in machine learning for generating model information to be set to a system that is configured to generate second output data from first output data, the first output data being generated by processing input data with use of the model information, the computer being configured to: obtain analysis input data; generate, from the analysis input data, first to-be-analyzed output data based on an arbitrary generation condition; generate second to-be-analyzed output data from the first to-be-analyzed output data; analyze the second to-be-analyzed output data; and generate, as the learning data, data including the analysis input data and the first to-be-analyzed output data in a case where the second to-be-analyzed output data fulfills a user's demand.

Abstract: A computing machine managing a template manages a document format, a template, and a cluster generated on the basis of a classification result based on a position of the document in a feature space in such a manner that they correspond to one another; determines whether a cluster to which a target document can belong is present on the basis of a position, in the feature space, of the target document in a case of detecting an opportunity of generating a template of the target document; registers the template of the target document in a case of determining that the cluster to which the target document can belong is not present; generates a cluster corresponding to the registered template; and manages a document format of the target document, the registered template, and the generated cluster in such a manner that they correspond to one another.

Abstract: A computer that extracts an attribute which is a text string contained in an predetermined examination target document stores template information for managing a plurality of templates in which a type of attribute is defined, executes a text recognition process on image data of the document, extracts an attribute corresponding to the type of attribute using a result of the text recognition process and the plurality of templates, selects a template based on the extracted attribute, generates output information that includes the attribute extracted using the selected template and is used for the examination; determines a type of confirmation operation performed on the output information, before the examination, based on a comparison result between an evaluation value indicating credibility of the output information and a threshold, and corrects the determined type of confirmation operation based on the text string contained in the document.