727 results about "Text graph" patented technology

A method for presenting advertising in an interactive service provided on a computer network, the service featuring applications which include pre-created, interactive text / graphic sessions is described. The method features steps for presenting advertising concurrently with service applications at the user terminal configured as a reception system. In accordance with the method, the advertising is structured in a manner comparable to the service applications enabling the applications to be presented at a first portion of a display associated with the reception system and the advertising presented at a second portion. Further, steps are provided for storing and managing advertising at the user reception system so that advertising can be pre-fetched from the network and staged in anticipation of being called for presentation. This minimizes the potential for communication line interference between application and advertising traffic and makes the advertising available at the reception system so as not to delay presentation of the service applications. Yet further the method features steps for individualizing the advertising supplied to enhance potential user interest by providing advertising based on a characterization of the user as defined by the users interaction with the service, user demographics and geographical location. Yet additionally, advertising is provided with transactional facilities so that users can interact with it.

A system and method for computing confidence in an output of a text recognition system includes performing character recognition on an input text image with a text recognition system to generate a candidate string of characters. A first representation is generated, based on the candidate string of characters, and a second representation is generated based on the input text image. A confidence in the candidate string of characters is computed based on a computed similarity between the first and second representations in a common embedding space.

Textual image coding involves coding textual portions of an image. In an example embodiment, a textual block of an image is decomposed into multiple base colors and an index map, with the index map having index values that each reference a base color so as to represent the textual block. A set of neighbor index values are ascertained for a particular index of the index map. A context that matches the neighbor index values is generated from among multiple contexts. The matching context includes a set of symbols. At least one symbol-to-value mapping is determined based on the matching context and a symbol to which the particular index corresponds. The particular index is remapped to a particular value in accordance with the symbol-to-value mapping and the symbol to which the particular index corresponds.

Some embodiments provide a method that efficiently designs a document. The method provides the user with a selection of templates, each with a default configuration for content. The method provides the user with a selection of page designs to add to a selected template. The method adds a selected page design to a document that is based on the selected template. Some embodiments provide methods for modifying default content of template documents with default text fields. When a user selects a default text field, the method of some embodiments selects the entire default text field for editing by the user. In some embodiments, the method highlights a text field selected by the user. Also, in some embodiments, the method deletes the content of the text field when the user provides new content for the selected field. In some embodiments, the new content is text, image, or another type of content.

The invention relates to an automatic nameplate recognition method and device, computer equipment and a storage medium. The method comprises the steps: obtaining a to-be-identified nameplate image; performing perspective transformation processing on the nameplate image to obtain a corrected image; extracting a character region in the corrected image to obtain a text image; based on convolutional recurrent neural network processing, performing conversion processing on the text image to obtain character information. According to the method, the perspective correction is performed on the nameplate image in the preprocessing stage to obtain the corrected image, and the accuracy of subsequent text recognition is improved. The text image in the corrected image is extracted through the text extraction box, the subsequent recognition range is narrowed, and the retrieval efficiency is improved. The convolutional network and the recurrent neural network are used to effectively identify the intrinsic context information in the text, convergence in detection is faster, and the recall rate of text detection and the accuracy of word-level detection box segmentation are improved.