A document scanner includes an enclosure with a scanning area. A transparent platform in the scanning area allows a user to position a document for authentication. A top camera takes a picture of the top of the document and a bottom camera takes a picture of the bottom under multiple light conditions including UV, IR, and white light. Mirrors reduce the enclosure size and multiple computers within the enclosure share work to process image data and determine document type. Types are searched in order based historically detected types. Barcode data is decoded and image samples are filtered as one of the computers finds a match. Security features are checked for the detected type and fake variants of the detected type are checked. Card information and formatting is validated and face data captured from a face camera and as shown on the document are matched against a database of banned users.

Disclosed is a transparency detecting method based on machine vision. The transparency detecting method includes 1) operating a Secchi disk to start the water transparency measurement, and turning on the camera for shooting; 2). determining a critical position of the Secchi disk; 3) identifying a water ruler and calculating a reading of the water ruler; 4) outputting and displaying the calculated reading.

A method for training a text positioning model includes: obtaining a sample image, where the sample image contains a sample text to be positioned and a text marking box for the sample text; inputting the sample image into a text positioning model to be trained to position the sample text, and outputting a prediction text box for the sample image; obtaining a sample prior anchor box corresponding to the sample image; and adjusting model parameters of the text positioning model based on the sample prior anchor box, the text marking box and the prediction text box, and continuing training the adjusted text positioning model based on a next sample image until model training is completed, to generate a target text positioning model.

A commodity sales data processing apparatus includes an image processor and a controller. The image processor captures an image including a symbol. The symbol includes discount information relating to a discount on a price of a commodity. The controller acquires commodity information that uniquely specifies the commodity. The controller extracts a region from the image captured by the camera. The region includes the symbol. The controller transmits, to a server, an image of the region extracted by the controller. The controller acquires, from the server, the discount information based on the image transmitted to the server. The controller registers the commodity information acquired by the controller and a discounted price of the commodity based on the discount information acquired by the controller in association with each other.

An identification card authenticity determining method based on deep learning according to the disclosure for automatically checking authenticity of an identification card includes: inputting identification card data to a feature information extraction model to extract pieces of feature information, expressing an indicator for checking authenticity of the identification card, from the identification card data; inputting the extracted pieces of feature information to a classification model to determine authenticity of the identification card; and when it is determined that the identification card is falsified, extracting a class activation map, where a falsification region of the identification card data is activated, from the pieces of feature information.

An information processing apparatus includes a processor configured to extract a mark specified in advance from an image of a document; and acquire a character string by performing character recognition on a region located in a particular direction with respect to a position of the mark, the direction being associated in advance with the mark.

The present disclosure discloses methods and systems for automatically detecting Infrared (IR) security mark based on unknown halftone frequency information. The method includes receiving a document from a user including an IR security mark. The document is scanned. Then, one or more halftone frequencies associated with the IR security mark portion are estimated. Based on the estimation, the IR security mark portion is classified into a background region and the IR marked region including the IR security mark. The IR security mark is extracted and pixels falling in the IR marked region are reconstructed to identify content in the IR security mark. Finally, the identified content is compared with one or more pre-stored IR security marks to ascertain the presence of the IR security mark in the document for further assessment. This way, the method automatically detects the IR security mark in the document.

A method for processing text in an image, an electronic device and a storage medium are provided in the present application. A user operation instruction carrying location information is acquired, and the location information is configured to indicate an operation location of a user's operation performed on the image. Target text corresponding to the location information in the image is identified, according to the user operation instruction. A display element is displayed overlying on the image, and the target text is displayed on the display element.

Described embodiments relate to a method comprising: determining a candidate document comprising image data and character data and extracting the image data and the character data from the candidate document. The method comprises providing, to an image-based numerical representation generation model, the image data, and generating, by the image-based numerical representation generation model, an image-based numerical representation of the image data. The method comprises providing, to a character-based numerical representation generation model, the character data; and generating, by the character-based numerical representation generation model, a character-based numerical representation of the character data. The method comprises providing, to a consolidated image-character based numerical representation generation model, the image-based numerical representation and the character-based numerical representation; and generating, by the consolidated image-character based numerical representation generation model, a combined image-character based numerical representation of the candidate document.

A text recognition method and apparatus, a storage medium, and an electronic device. Said method comprises: acquiring a text image (S101); determining at least one text box from the text image, each text box corresponding to at least one word (S102); determining, from the at least one text box, a text box to be recognized (S103); determining, from the text image, a picture unit corresponding to the text box to be recognized (S104); rotating the picture unit to a target pose (S105); and performing text recognition on the picture unit in the target pose, and acquiring a target recognition result (S106). The method, apparatus, storage medium, and electronic device can recognize a text unit in a text having a large inclination angle.