Embodiments of the present disclosure include a method that obtains a digital image. The method includes extracting a word block from the digital image. The method includes processing the word block by evaluating a value of the word block against a dictionary. The method includes outputting a prediction equal to a common word in the dictionary when a confidence factor is greater than a predetermined threshold. The method includes processing the word block and assigning a descriptor to the word block corresponding to a property of the word block. The method includes processing the word block using the descriptor to prioritize evaluation of the word block. The method includes concatenating a first output and a second output. The method includes predicting a value of the word block.

An image processing apparatus includes a first image generator and a second image generator. The first image generator generates a first image, including a predetermined ruled-line image and an inscription image, from a second sheet in a sheet group. The sheet group is obtained by stacking multiple sheets including a single first sheet and the second sheet. The first sheet has inscription information inscribed thereon. The second sheet has the inscription image corresponding to the inscription information transferred thereon and includes the ruled-line image. The second image generator generates a second image in which a surplus image is removed from the first image generated by the first image generator in accordance with a learning model that has learned to remove the surplus image different from the ruled-line image and the inscription image.

An image processing apparatus includes a first image generator and a second image generator. The first image generator generates a first image, including a predetermined ruled-line image and an inscription image, from a second sheet in a sheet group. The sheet group is obtained by stacking multiple sheets including a single first sheet and the second sheet. The first sheet has inscription information inscribed thereon. The second sheet has the inscription image corresponding to the inscription information transferred thereon and includes the ruled-line image. The second image generator generates a second image in which a surplus image is removed from the first image generated by the first image generator in accordance with a learning model that has learned to remove the surplus image different from the ruled-line image and the inscription image.

A method for recognizing handwritten text is disclosed. The method comprises receiving data comprising a sequence of ink points; applying the received data to a neural network-based sequence classifier trained with a Connectionist Temporal Classification (CTC) output layer using forced alignment to generate an output; generating a character hypothesis as a portion of the sequence of ink points; applying the character hypothesis to a character classifier to obtain a first probability corresponding to the probability that the character hypothesis includes the given character; processing the output of the CTC output layer to determine a second probability corresponding to the probability that the given character is observed within the character hypothesis; and combining the first probability and the second probability to obtain a combined probability corresponding to the probability that the character hypothesis includes the given character.

A book made up of pages is described. At least some of the pages contain both space for manually-created visual content, and instances of preprinted indexing target symbols. Each of the indexing target symbol instances has at least a portion within one inch of three unbound page edges. When the book is closed, the instances of each particular indexing target symbol are in a substantially collinear stack that is substantially perpendicular to the faces of the pages.

Character recognition processing suitable to a handwritten character area and a printed character area among character areas in a scanned image of a document is performed. Next, character recognition results for the handwritten character area and character recognition results for the printed character area are integrated and a likelihood indicating a probability of being an extraction target is calculated for a candidate character string that is an extraction candidate among the integrated character recognition results and a character string that is the item value is determined. Then, at the time of the determination, different evaluation indications are used in a case where a character originating from the handwritten character area is included in characters constituting the candidate character string and in a case where such a character is not included.

Character recognition processing suitable to a handwritten character area and a printed character area among character areas in a scanned image of a document is performed. Next, character recognition results for the handwritten character area and character recognition results for the printed character area are integrated and a likelihood indicating a probability of being an extraction target is calculated for a candidate character string that is an extraction candidate among the integrated character recognition results and a character string that is the item value is determined. Then, at the time of the determination, different evaluation indications are used in a case where a character originating from the handwritten character area is included in characters constituting the candidate character string and in a case where such a character is not included.

Method, computer readable medium, and apparatus of recognizing character zone in a digital document. In an embodiment, the method includes classifying a segment of the digital document as including text, calculating at least one parameter value associated with the classified segment of the digital document, determining, based on the calculated at least one parameter value, a zonal parameter value, classifying the segment of the digital document as a handwritten text zone or as a printed text zone based on the determined zonal parameter value and a threshold value, the threshold value being based on a selection of an intersection of a handwritten text distribution profile and a printed text distribution profile, each of the handwritten text distribution profile and the printed text distribution profile being associated with a zonal parameter corresponding to the determined zonal parameter value, and generating, based on the classifying, a modified version of the digital document.

In implementations of systems for generating stroked paths, a computing device implements a stroked path system to receive input data describing a vector object having a filled path. The stroked path system generates a medial axis for the filled path by performing a medial axis transform on a boundary of the filled path. A stroke width is estimated based on distances between the medial axis and the boundary of the filled path that are normal to the medial axis. The stroked path system generates a stroked path for display in a user interface that is visually similar to the filled path based on the medial axis and the stroke width.

Position detection methods and systems are disclosed herein. The position detection method of detecting a position in an operation surface pointed by a pointing element includes obtaining a first taken image with the first infrared camera, obtaining a second taken image with the second infrared camera, removing a noise component from the first and second images converting the first and second taken into converted images without the noise component, forming a difference image between the first converted taken image and the second converted taken image, extracting a candidate area in which a disparity amount between the first converted taken image and the second converted taken image is within a predetermined range, detecting a tip position of the pointing element from the candidate area, and determining a pointing position of the pointing element and whether or not the pointing element had contact with the operation surface based on the detecting.