Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for detecting text instances of arbitrary shapes, sizes, and locations. In one aspect, a method comprises processing an image depicting one or more text instances, generating a respective prediction for each character in a sequence of characters that are predicted to be depicted in the text instance, the respective prediction comprising a respective character class to which the predicted character belongs, the respective character class selected from a set that includes printable character classes and a space character class and a bounding box that contains the character within the image, and grouping the sequence of characters into a plurality of words based on locations of characters that are predicted to belong to the space character class.

An image processing apparatus counts at least one of the number of pixels having an identical color to a target pixel, the number of pixels having a similar color to the target pixel, and the number of pixels having a different color from the target pixel in a target window, and determines an attribute of the target pixel based on a result of the counting.

A complex background-oriented optical character recognition method and device are provided. The method of the present invention includes: collecting image information to obtain a collected image; according to character characteristics, acquiring a target character region from the collected image, and taking same as a target object; extracting character edge information in the target object using a differential method to obtain an extracted image; superposing the target object and the extracted image to obtain a recovery image; conducting inversion and Gaussian filtration processing on the recovery image to obtain a processed image; searching for a target character location in the processed image; and recognizing the target character location. On this basis, accurate and quick locating and recognition of characters can be realized on the basis of effectively suppressing background noise and highlighting character information.

An article image data acquirer acquires article image data as a target of optical character recognition (OCR). An inference result data generator generates first inference result data and second inference result data by inputting the article image data as the target of the OCR into a trained model. An inference result data outputter outputs the first inference result data and the second inference result data. An image filter generator generates a first image filter based on the first inference result data and a second image filter based on the second inference result data. An image filter outputter outputs the first image filter and the second image filter.

An article image data acquirer acquires article image data as a target of optical character recognition (OCR). An inference result data generator generates first inference result data and second inference result data by inputting the article image data as the target of the OCR into a trained model. An inference result data outputter outputs the first inference result data and the second inference result data. An image filter generator generates a first image filter based on the first inference result data and a second image filter based on the second inference result data. An image filter outputter outputs the first image filter and the second image filter.

A multi-module imaging system and an image-synchronization method are provided. The multi-module imaging system includes a photographic component having multiple photosensitive modules, an image signal processor and a data processor. The different photosensitive modules generate multiple sets of motion images respectively. The image signal processor then retrieves continuous frame images from each of the sets of motion images. The data processor obtains multiple frames generated at the same time from the continuous frame images and generates a composite frame that vertically combines the multiple frames by performing a vertical encoding procedure. Therefore, the multiple sets of motion images are encoded to be continuously-outputted multiple composite frames. Accordingly, the multi-module imaging system can synchronously output the frames that are generated by different photosensitive modules.

A multi-module imaging system and an image-synchronization method are provided. The multi-module imaging system includes a photographic component having multiple photosensitive modules, an image signal processor and a data processor. The different photosensitive modules generate multiple sets of motion images respectively. The image signal processor then retrieves continuous frame images from each of the sets of motion images. The data processor obtains multiple frames generated at the same time from the continuous frame images and generates a composite frame that vertically combines the multiple frames by performing a vertical encoding procedure. Therefore, the multiple sets of motion images are encoded to be continuously-outputted multiple composite frames. Accordingly, the multi-module imaging system can synchronously output the frames that are generated by different photosensitive modules.

In some instances, a method is provided. The method comprises: obtaining, by a computing system, a plurality of documents, wherein at least one document, of the plurality of documents, comprises one or more circular shaped user indications, wherein each of the one or more circular shaped user indications indicates a user selection of a design or text within the associated circular shaped user indication; determining, by the computing system, circular shaped identification information for a document, of the plurality of documents based on inputting the document into a trained machine learningartificial intelligence (ML-AI) model, wherein the circular shaped identification information indicates the user selection of the design or the text within the associated circular shaped user indication; and performing, by the computing system, one or more actions based on the circular shaped identification information.

In some instances, a method is provided. The method comprises: obtaining, by a computing system, a plurality of documents, wherein at least one document, of the plurality of documents, comprises one or more circular shaped user indications, wherein each of the one or more circular shaped user indications indicates a user selection of a design or text within the associated circular shaped user indication; determining, by the computing system, circular shaped identification information for a document, of the plurality of documents based on inputting the document into a trained machine learningartificial intelligence (ML-AI) model, wherein the circular shaped identification information indicates the user selection of the design or the text within the associated circular shaped user indication; and performing, by the computing system, one or more actions based on the circular shaped identification information.

The present disclosure generally relates to embodiments of document scanning processes using a dynamic flash and providing access to scanned documents.