Character detection method and apparatus

Abstract

The embodiment of the invention discloses a character detection method and apparatus. The character detection method includes the steps: performing feature extraction of a plurality of abstraction layers on an image to be detected by means of a feature extraction network; predicting the probability that each pixel point in the image to be detected is a character pixel point, and when each pixel point is a character pixel point, the positional information of a bounding box of a character, opposite to the pixel point, by means of a character detection network; based on the prediction result of the character detection network, determining the positional information of the bounding box of each candidate character; inputting the extracted features into a character mapping network, and performing transformation on a feature diagram output from the character mapping network to generate a character vector; determining the neighbour candidate character of each candidate character in the image to be detected, and connecting the each candidate character with the related neighbour candidate character into a character set; and according to the positional information of the bounding box of eachcandidate character in the character set, determining the character region of the image to be detected. The character detection method improves accuracy of detection of irregular characters.

Description

technical field [0001] The embodiments of the present application relate to the field of computer technology, specifically to the field of image processing technology, and in particular to a text detection method and device. Background technique [0002] With the development of computer vision technology, image-based text detection and text recognition technology has been more and more widely used. For example, in document processing, geographical location reading, image retrieval, etc., text detection and text recognition have many practical application. [0003] In the field of Optical Character Recognition (OCR), a text frame is usually defined as a rectangular detection frame, and connections between texts are usually straight lines. However, there are a large number of distorted, deformed and other irregular text combinations in the actual collected data, for example, the text in the image is distorted due to image distortion or shooting angle, or some deformed charact...

AI Technical Summary

Problems solved by technology

However, there are a large number of distorted, deformed and other irregular text combinations in the actual collected data, for example, the text in the image is distorted due to image distortion or shooting angle, or some deformed characters are used in some designs such as trademarks and badges

[0004] The existing text detection algorithms require the connection between the basic components in the image to be in a straight line, or require pixel-level annotation accuracy, which is not easy to apply in a wider range of scenarios

Images