Text recognition method and device, electronic equipment and storage medium

Abstract

The invention discloses a text recognition method and device, electronic equipment and a storage medium. The method comprises the steps of obtaining a to-be-recognized text image; extracting a featuremap of the to-be-recognized text image based on a pre-constructed text detection network, and performing text pixel classification on the fused feature map to generate at least one candidate textbox,the text detection network comprising a first feature extraction layer, a second feature extraction layer and a third feature extraction layer, the second feature extraction layer up-sampling an output result of the first feature extraction layer, and the third feature extraction layer down-sampling an output result of the second feature extraction layer; and according to a preset target text format, screening the candidate textboxes to obtain a target textbox, and identifying the target textbox to obtain an identification result. Based on this, the high-resolution information of the low-level features and the high-semantic information of the high-level features can be utilized at the same time, so that text pixel position detection is more accurate, and the text recognition accuracy andefficiency are improved.

Description

technical field [0001] The present application generally relates to the technical field of image processing, and specifically relates to a text recognition method, device, electronic equipment and storage medium. Background technique [0002] Smart dining cabinets, also known as distribution and ordering systems, are mainly used to store fast food, which facilitates people's daily life. In actual use, the smart dining cabinet can verify the identity of the user by pressing buttons and scanning the meal code to complete the meal pickup. [0003] In the process of realizing the present invention, the inventor found that the recognition accuracy of the related technology is low, especially when there is a text with a rotation or bending angle on the meal code, the error is larger, and the time consumed for detection is long. Contents of the invention [0004] In view of the above defects or deficiencies in related technologies, it is desired to provide a text recognition met...

AI Technical Summary

Problems solved by technology

[0003] In the process of realizing the present invention, the inventor found that the accuracy of the related technology to recognize the meal code is low, especially when there is a text with a rotation or bending angle on the meal code, the error is larger, and the time consumed for the detection at the same time is long

Images