The present disclosure provides a method, a device, and a computer readable storage medium for recognizing mixed typeset texts. The method includes: detecting one or more bounding boxes each containing a text paragraph from a picture; determining a text typesetting direction of each bounding box based on geometric characteristics of the bounding box, where the text typesetting direction includes horizontal and vertical; and inputting the bounding box into a text recognition network corresponding to the text typesetting direction, based on the text typesetting direction of the bounding box, to recognize texts in the bounding box.

An information processing apparatus includes a processor configured to acquire (i) an image including characters and (ii) a character-recognition result obtained by applying character recognition on the image, and display, to a viewer of the character-recognition result, each character in the image and a recognized character corresponding to the character in a uniform size and at positions adjusted to indicate correspondence between the character and the recognized character.

A method clusters each character on a document into one of a plurality of clusters based on widths of at least a portion of the characters on the document and measures distances between characters on the document. A threshold for each of the plurality of clusters is calculated based on at least a portion of the distances between characters in each cluster. The method then segments characters into units using the thresholds for the plurality of clusters. A distance between two characters in the document is compared to a threshold for a cluster to classify the two characters as being part of a unit when the distance is less than the threshold and not being part of the unit when the distance is greater than the threshold. Then, the method performs a recognition process on the document using the units.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for neural network-based optical character recognition. An embodiment of the system may generate a set of bounding boxes based on reshaped image portions that correspond to image data of a source image. The system may merge any intersecting bounding boxes into a merged bounding box to generate a set of merged bounding boxes indicative of image data portions that likely portray one or more words. Each merged bounding box may be fed by the system into a neural network to identify one or more words of the source image represented in the respective merged bounding box. The one or more identified words may be displayed by the system according to a standardized font and a confidence score.

Disclosed is an electronic device including: a memory, and a processor operatively connected to the memory. The memory stores instructions which, when executed, cause the processor to: obtain handwriting data including at least one letter; align the at least one letter with a reference line to generate target handwriting data; change at least one of a position or an angle of the at least one letter to generate distorted handwriting data; obtain correction information for correcting the distorted handwriting data to correspond to the target handwriting data; and store the correction information in the memory.

Embodiments disclosed herein provide for systems and methods of separating characters associated with ligatures in digitized documents. The systems and methods provide for a ligature detection engine configured to identify the ligatures, and a ligature processing engine configured to identify and remove the glyphs attaching the separate characters forming the ligature.

A glyph-aware method for underlining text in digital typography includes identifying first and second intersection coordinates where first and second bounds of an underline region of the text intersect with an outline path of a glyph in the text. Where such intersections occur, a portion of the outline path of the glyph between the first and second intersection coordinates is copied. First and second offset coordinates for the underline are determined by adding or subtracting an offset to the first and second intersection coordinates. A first underline outline path is constructed in the underline region, where the first underline outline path includes the copied of the outline path of the glyph between the first and second intersection coordinates. A display device renders an underline, at least partially, along the first underline outline path between the first and second offset coordinates in the underline region of the text.

A glyph-aware method for underlining text in digital typography includes identifying first and second intersection coordinates where first and second bounds of an underline region of the text intersect with an outline path of a glyph in the text. Where such intersections occur, a portion of the outline path of the glyph between the first and second intersection coordinates is copied. First and second offset coordinates for the underline are determined by adding or subtracting an offset to the first and second intersection coordinates. A first underline outline path is constructed in the underline region, where the first underline outline path includes the copied of the outline path of the glyph between the first and second intersection coordinates. A display device renders an underline, at least partially, along the first underline outline path between the first and second offset coordinates in the underline region of the text.

An information processing apparatus includes a processor programmed to: acquire from a video a first subtitle in a first language, translate the first subtitle in the first language into a second subtitle in a second language, and display a notification for the second subtitle in a case where a display time for the first subtitle in the first language is shorter than a recognition time for the second subtitle in the second language.

A method for estimating text heights of text line images includes estimating a text height with a sequence recognizer. The method further includes normalizing a vertical dimension and/or position of text within a text line image based on the text height. The method may also further include calculating a feature of the text line image. In some examples, the sequence recognizer estimates the text height with a machine learning model.