A text recognition method includes: acquiring an image including text information, the text information including M characters, M being a positive integer greater than 1; performing text recognition on the image to acquire character information about the M characters; recognizing reading direction information about each character in accordance with the character information about the M characters, the reading direction information being used to indicate a next character corresponding to a current character in a semantic reading order; and ranking the M characters in accordance with the reading direction information about the M characters to acquire a text recognition result of the text information.

An image processing system which corrects a text obtained by optical character recognition (OCR) using a neural network which has performed learning based on a falsely recognized portion of OCR and a text near the falsely recognized portion is provided. The image processing system acquires a neural network model which has been trained based on learning data in which first text information included in print data and second text information acquired by performing optical character recognition (OCR) processing on an image that is based on the print data are associated with each other, acquires an image obtained by a scanner, acquires third text information which is generated by performing OCR processing on the image obtained by the scanner, and outputs fourth text information according to inputting of the third text information based on the neural network model.

The present disclosure provides techniques for encoding and decoding characters for optical character recognition. The techniques involve determining sets of numbers for encoding a character set where each number in a particular set of numbers for encoding a particular character is mapped to a graphical unit (e.g., radical) of the particular character. A mapping between each set of numbers in the possible encodings and the character set may be determined based the closest character already encoded. A machine learning model may be trained to perform optical character recognition using training data labeled using the set of encodings and the mappings.

According to implementations of the subject matter described herein, there is provided a solution for text recognition in an image. In this solution, a target text line area, which is expected to include a text to be recognized, is determined from an image. Probability distribution information of a character model element(s) present in the target text line area is determined using a single character model. The single character model is trained based on training text line areas and respective ground-truth texts in the training text line areas. Texts in the training text line areas are arranged in different orientations, and/or the ground-truth texts comprise texts are related to various languages (e.g., texts related to a Latin and an Eastern languages). The text in the target text line area can be determined based on the determined probability distribution information. The single character model enables more efficient and convenient text recognition.

Ideogram character analysis includes partitioning an original ideogram character into strokes and mapping each stroke to a corresponding stroke identifier (id) to create an original stroke id sequence that includes stroke identifiers. A candidate ideogram character that has a candidate stroke id sequence within a threshold distance to the original stroke id sequence is selected. One or more embodiments may create a new phrase by replacing the original ideogram character with the candidate ideogram character in a search phrase. One or more embodiments perform a search using the search phrase and the new phrase to obtain a result and present the result. One or more embodiments may replace an original ideogram character in a character recognized document with the candidate ideogram character and store the character recognized document.

A method and system to generate training data for a deep learning model in memory instead of loading pre-generated data from disk storage. A corpus may be stored as lines of text. The lines of text can be manipulated in the memory of a central processing unit (CPU) of a computing system, using asynchronous multi-processing, in parallel with a training process being conducted on the system's graphics processing unit (GPU). With such an approach, for a given line of text, it is possible to take advantage of different fonts and different types of image augmentation without having to put the images in disk storage for subsequent retrieval. Consequently, the same line of text can be used to generate different training images for use in different epochs, providing more variability in training data (no training sample is trained on more than once). A single training corpus may yield many different training data sets. In one aspect, the model being trained is a deep learning model, which may be one of several different types of neural networks. The training enables the deep learning model to perform OCR on line images.

A computer implemented method for optical character recognition (OCR) of a character string in a text image. The method efficiently combines two different OCR engines with the computation that needs to be done by the second OCR engine depending on the results found by the first OCR engine. This method provides, in particular, a high speed and accurate results when the first OCR engine is fast and the second OCR engine is accurate. The combination is possible because the second OCR engine identifies each segment to be processed by the second OCR engine without needing to process all segments.

A method and system to generate training data for a deep learning model in memory instead of loading pre-generated data from disk storage. A corpus may be stored as lines of text. The lines of text can be manipulated in the memory of a central processing unit (CPU) of a computing system, using asynchronous multi-processing, in parallel with a training process being conducted on the system's graphics processing unit (GPU). With such an approach, for a given line of text, it is possible to take advantage of different fonts and different types of image augmentation without having to put the images in disk storage for subsequent retrieval. Consequently, the same line of text can be used to generate different training images for use in different epochs, providing more variability in training data (no training sample is trained on more than once). A single training corpus may yield many different training data sets. In one aspect, the model being trained is a deep learning model, which may be one of several different types of neural networks. The training enables the deep learning model to perform OCR on line images.

A method and a system for converting a font of a Chinese character in an image, a computer device and a medium are disclosed. A specific implementation of the method includes: acquiring a stroke of a to-be-converted Chinese character in the image and spatial distribution information of the stroke; and generating a Chinese character in a target font that corresponds to the to-be-converted Chinese character in the image according to the stroke of the to-be-converted Chinese character, the spatial distribution information of the stroke and standard stroke information of the target font, to replace the to-be-converted Chinese character.

A processing method for character stroke and related device are provided. The method comprises: obtaining handwriting information of a first handwriting point and handwriting information of a second handwriting point in a character stroke, the handwriting information comprising coordinate information; determining a display effect related to the first handwriting point according to the handwriting information of the first handwriting point and the handwriting information of the second handwriting point; rendering the display effect related to the first handwriting point within a display range of the first handwriting point. The display manner of the character stroke can be enriched through above manner, thereby improving the user experience.