Provided are character image processing methods and apparatuses, devices, storage medium, and computer programs. The character image processing method mainly comprises: obtaining at least one image block containing a character in a character image to be processed; obtaining image block form transformation information of the image block on the basis of a neural network, the image block form transformation information being used for changing a character orientation in the image block to a predetermined orientation, and the neural network being obtained by means of training using an image block sample having form transformation label information; performing form transformation processing on the character image to be processed according to the image block form transformation information; and performing character recognition on the character image to be processed which is subjected to the form transformation.

A method for splitting text line images includes receiving a text line image and identifying that the text line image comprises a plurality of zones, wherein each zone includes text whose font differs from the text of adjacent zones. The method further includes selecting a splitting position between multiple zones and splitting the text line image at the splitting position into a plurality of image segments, wherein each image segment contains at least one zone of the text line image and performing optical character recognition on each image segment to recognize a text segment of the image segment. In certain implementations, the method further includes generating one or more confidence measurements and selecting a splitting position that corresponds to a large gradient in the confidence measurement.

A method, an apparatus and an electronic device of character segmentation are disclosed. The method includes obtaining character segmentation points of a character image to be segmented as candidate segmentation points using a predetermined segmentation point generation algorithm, the character image to be segmented being a foreground character image that is obtained by removing a background image from an original grayscale character image; selecting and obtaining correct segmentation points from the candidate segmentation points based on the original grayscale character image and a pre-generated segmentation point classifier; and performing character segmentation for the character image to be segmented based on the correct segmentation points. Using the method provided by the present disclosure, candidate segmentation points can be filtered to obtain correct segmentation points, thus avoiding overly segmentation of a character image having phenomena such as character breaking, and thereby achieving an effect of improvement on the accuracy of character segmentation.

A character translation method performed by a character translation apparatus according to one embodiment of the present invention may comprise the steps of: obtaining image contents; recognizing characters of a first language on the image contents and a sentence determination symbol of the first language; extracting a sentence of the first language composed of the recognized characters, on the basis of the recognized sentence determination symbol; producing, on the basis of the extracted sentence of the first language, a sentence to be translated using user event information; and translating the generated sentence to be translated into a second language and displaying the sentence translated into the second language.

A method for estimating text heights of text line images includes estimating a text height with a sequence recognizer. The method further includes normalizing a vertical dimension and/or position of text within a text line image based on the text height. The method may also further include calculating a feature of the text line image. In some examples, the sequence recognizer estimates the text height with a machine learning model.

Described herein is a mechanism for visual recognition of items or visual search using Optical Character Recognition (OCR) of text in images. Recognized OCR blocks in an image comprise position information and recognized text. The embodiments utilize a location-aware feature vector created using the position and recognized information in each recognized block. The location-aware features of the feature vector utilize position information associated with the block to calculate a weight for the block. The recognized text is used to construct a tri-character gram frequency, inverse document frequency (TGF-IDP) metric using tri-character grams extracted from the recognized text. Features in location-aware feature vector for the block are computed by multiplying the weight and the corresponding TGF-IDF metric. The location-aware feature vector for the image is the sum of the location-aware feature vectors for the individual blocks.

A text recognition method and apparatus disclosed. The text recognition method includes: obtaining a to-be-detected image; determining a target text detection area in the to-be-detected image, where the target text detection area includes target text in the to-be-detected image, and the target text detection area is a polygonal area including m vertex pairs, m being a positive integer greater than 2; correcting the polygonal area to m1 rectangular areas to obtain a corrected target text detection area; and performing text recognition on the corrected target text detection area to determine the target text, and outputting the target text.

A text line detecting method includes: performing a preprocessing operation on an image to be detected to generate connected domains; performing a filtering operation on the connected domains to obtain connected domains that meet a preset requirement; and perform a text line recognizing operation according to a processing result. In the text line detecting method according to the embodiments of the present invention, by means of performing the preprocessing operation and the filtering operation on the image to be detected to obtain the connected domains that meet the preset requirement, and then performing the text line recognizing operation according to the processing result,detection and recognition accuracy of a text line are improved, and detection and recognition efficiencies of the text line are improved.

A text partitioning method, a text classifying method, an apparatus, a device and a storage medium, wherein the method includes: parsing a content image, to obtain a target text in a text format; according to a line break in the target text, partitioning the target text into a plurality of text sections; and according to a first data-volume threshold, partitioning sequentially the plurality of text sections into a plurality of text-to-be-predicted sets, wherein a data volume of a last one text section in each of the text-to-be-predicted sets is greater than a second data-volume threshold.

Systems, methods and non-transitory computer readable media for selecting content for presentation in retail stores are provided. Location data associated with a device associated with an individual in a retail store, such as a shopping cart, may be obtained. A data structure including a plurality of data records may be accessed. Each data record may associate a content provider, a region of the retail store and a modifiable bid amount. A group of data records that match the location data of the plurality of data records may be identified. A particular data record of the group may be selected based on the bid amounts. The particular data record may be associated with a particular content provided and a particular bid amount. Content associated with the particular content provider may be presented. An account associated with the particular content provider may be updated based on the particular bid amount.