According to an embodiment, an information processing apparatus comprises a first interface, a second interface, a third interface, and a processor. The first interface acquires a character string image that includes a character string. The second interface transmits and receives data to and from an internal device through a first network. The third interface transmits and receives data to and from an external device through a second network. The processor transmits, if the character string image includes personal information, the character string image to the internal device through the second interface and receive an input of the character string from the internal device and transmits, if the character string image does not include the personal information, the character string image to the external device through the third interface and receive an input of the character string from the external device.

A system for generating textual instructions for manufacturers from hybrid textual and image data includes a manufacturing instruction generator that may generate a language processing module from a first training set including at least a training annotated file describing at least a first product to manufacture, the at least an annotated file containing one or more textual data, and at least an instruction set containing one or more manufacturing instructions to manufacture the at least a first product. Manufacturing instruction generator may use the language processing to generate textual instructions for manufacturers from at least an annotated file and may initiate manufacture using the generated manufacturing instructions.

A method to automatically adjust a user interface of a mobile device for readability is provided. A processor retrieves an external capture of a display of a mobile device. A processor converts text in the external capture to a computer readable format. A processor determines a readability index of the external capture based on a comparison of the text in the external capture to user interface data of the mobile device. A processor, in response to the readability index being below a threshold value, adjusts at least one display parameter of a user interface of the mobile device.

“The present disclosure describes a method, an apparatus, and a non-transitory computer-readable medium for detecting sensitive text information such as privacy-related text information from a signal and modifying the signal by removing the detected sensitive text information therefrom. The apparatus receives the signal such as an image, a video clip, or an audio clip, and recognizes a text string therefrom. The apparatus then detects, from the text string, a substring based on a similarity between the substring and a regular expression, and modifies the signal by removing information related to the detected substring from the signal.”

“The present disclosure describes a method, an apparatus, and a non-transitory computer-readable medium for detecting sensitive text information such as privacy-related text information from a signal and modifying the signal by removing the detected sensitive text information therefrom. The apparatus receives the signal such as an image, a video clip, or an audio clip, and recognizes a text string therefrom. The apparatus then detects, from the text string, a substring based on a similarity between the substring and a regular expression, and modifies the signal by removing information related to the detected substring from the signal.”

According to an embodiment, the recognition apparatus includes an image interface, an input interface, and a processor. The image interface is configured to acquire a display screen image from an input device for inputting a character string included in a captured image in which recognition of the character string according to a first algorithm fails. The input interface is configured to input the character string to the input device. The processor is configured to acquire a result of character recognition processing performed on the display screen image according to a second algorithm different from the first algorithm, and input the character string based on the result of the character recognition processing to the input device through the input interface.

A training image in accordance with a way a hane occurs, which is found in actual handwriting, is generated. Among line segments constituting a handwritten character in a character image representing the handwritten character, a line segment at which a handwritten hane may occur is detected. Then, by performing processing to add a simulated hane to the end portion of the detected line segment, a training image is generated.

The method, system, and non-transitory computer-readable medium embodiments described herein provide for identifying invalid identification documents. In various embodiments, an application executing on a user device prompts the user device to transmit an image of the identification document. The application receives an image including the identification document in response to the identification document being within a field of view of a camera of the user device. The identification document includes a plurality of visual elements, and one or more visual elements of the plurality of visual elements are one or more invalidating marks. The application detects a predetermined pattern on the identification document in the image, the predetermined pattern formed from the one or more invalidating marks. The application determines that the identification document is invalid based on the detected predetermined pattern.

This application provides a method of detecting printing defects. The method includes obtaining a first image of each character in a reference image. A third image of each character is obtained based on the first image of each character, a fourth image of each character is obtained based on a second image of each character obtained from an image to be detected. Once a fifth image of each character is obtained based on the third image of each character, a sixth image of each character is obtained according to the fourth image and the fifth image of each character, a detection result of each character in the image to be detected is determined according to the fifth image and the sixth image of the each character.

A text correction engine meets different and changing end user requirements, with the ability to change a desired output by providing sufficient amounts of data, and by finetuning the appropriate text correction engine at the point of origin of the data. It is possible to retain confidentiality of data by retraining the base deep learning model at the base deep learning model's point of origin, to improve the base deep learning model's performance, making the base deep learning model more accurate for different contexts. Separate training of an end user model, leaving the base deep learning model intact, streamlines end user model training, and highlights desirable changes in the base deep learning model for further training or retraining.