A picture search method and apparatus, an electronic device, a computer-readable storage medium, and a computer program product, relating to the field of artificial intelligence that can obtain an OCR result of pictures in a preset picture library in response to a picture search request; traverse pictures which are not subjected to low-dimensional OCR processing and high-dimensional OCR processing in the preset picture library, and perform the low-dimensional OCR processing based on an OCR threshold on each of the traversed pictures to obtain a low-dimensional OCR result of each corresponding picture; determining a target picture matching a key character string in the preset picture library according to at least one of the low-dimensional OCR result and the high-dimensional OCR result of each picture; and determining the target picture as a search result of the picture search request, and displaying the search result.

A search system capable of searching for an image with a similar represented concept is provided. The search system includes an input unit, a text extraction unit, a tag obtaining unit, and a tag similarity calculation unit. When image data to which an image label is assigned and document data including the image label are supplied to the input unit, the text extraction unit is configured to extract tag-obtaining-purpose text data from the document data on the basis of the image label. The tag obtaining unit is configured to obtain a tag including at least a part of words included in the tag-obtaining-purpose text data. The tag similarity calculation unit is configured to calculate similarity between tags. It is possible to search for an image having a greatly different feature value of the image itself but having a similar represented concept.

An image database establishing method, a searching method, an electronic device and a storage medium. The method comprises: obtaining a target file which has target text information (S210); generating a target image corresponding to content expressed by the target text information based on the target text information (S220); and storing the target image to form an image database (S230). The above method solves the problem in the prior art that it is time-consuming and laborious to establish a database by manually filtering, analyzing and summarizing massive text files, and effectively improves the efficiency of establishing an image database.

The disclosure is for displaying a search result for products. A server may include a communication module, a memory including a database which stores product information in association with one or more product images corresponding to a product and text information related to the product, and a processor. The processor may receive a query image for an external object from an electronic device by using the communication module, select, from the database, a plurality of pieces of product information corresponding to the external object, based on similarities between the one or more product images and the query image, extract the text information for the external object included in the query image, determine a priority among the plurality of pieces of product information, based on a comparison between the extracted text information and the text information included in the selected plurality of pieces of product information, and transmit, to the electronic device, at least some of the plurality of pieces of product information and information on the priority, in response to the reception, by using the communication module.

Systems and methods are provided for relevance-based media content discovery. Relevance scores for segments of a media asset are calculated based on a time amount that at least one viewer has viewed the segments of the media asset. Segments are then chosen for display based on the relevance score. Users may select segments based on representative images of the segments.

A system for file image processing and extraction of content from images is provided. The system comprises a computer and an application. When executed on the computer, the application receives a source document containing areas of interest and normalizes the document to align with a stored template image. The application also applies metadata associated with the template image to the areas of interest to identify data fields in the normalized document and extracts data from the identified data fields. The application also processes the extracted data using at least character recognition systems and produces a static structure using at least the identified data fields, the fields containing the processed data. The areas of interest comprise portions of the source document containing text needed to create and populate fields suggested by the stored template image. Normalizing the source document comprises at least one of flipping, rotating, expanding, and shrinking the document.

A system for identifying and timing an athlete during a timed sporting event. The athlete is timed using image recognition technology in which one or more images of the athlete taken during the sporting event by a camera (106a, 106b, or 106c) is time-stamped to generate a finish time for the athlete. The athlete is identified by comparing one of the images taken during the sporting event with a profile image of the athlete.

An image processing apparatus includes a character recognition processing unit configured to execute character recognition processing on the image data, an acquisition unit configured to acquire one or more character string blocks included in the image data, from the image data, a selection unit configured to select a character string block to be used for setting of a file name, from among the one or more character string blocks acquired by the acquisition unit, and a setting unit configured to set the file name of image data by using a character recognition result of the character recognition processing unit for the character string block selected by the selection unit.

The present disclosure relates to a tag-based font recognition system that utilizes a multi-learning framework to develop and improve tag-based font recognition using deep learning neural networks. In particular, the tag-based font recognition system jointly trains a font tag recognition neural network with an implicit font classification attention model to generate font tag probability vectors that are enhanced by implicit font classification information. Indeed, the font recognition system weights the hidden layers of the font tag recognition neural network with implicit font information to improve the accuracy and predictability of the font tag recognition neural network, which results in improved retrieval of fonts in response to a font tag query. Accordingly, using the enhanced tag probability vectors, the tag-based font recognition system can accurately identify and recommend one or more fonts in response to a font tag query.

Provided are a method, a system, and a non-transitory computer-readable record medium for comparing common features of products and providing a comparison result. A product comparison method includes recognizing at least two comparable products from at least one image; displaying at least one common attribute of the at least two comparable products through a user interface; and based on the user interface receiving a user input that selects one of the at least one common attribute, as a selected attribute, providing a result of comparison between the at least two comparable products with regard to the selected attribute.