Text detection method, device and system based on depth relation reasoning and medium

Abstract

The invention discloses a text detection method, device and system based on depth relation reasoning and a storage medium, and the method comprises: obtaining a to-be-detected text image, and carrying out the geometric attribute estimation of a rectangular component in the to-be-detected text image through a pre-constructed and trained text component network, wherein the text component prediction network adopts a convolutional neural network in cross-layer connection; generating a plurality of local graphs according to the geometric attributes of the rectangular components; and performing deep reasoning on the local graph through a pre-constructed and trained deep relation reasoning network, and forming a text detection result according to a reasoning result link. According to the embodiment of the invention, the local graph is generated after the geometric attributes of the rectangular components in the to-be-detected text image are estimated, and the deep relation reasoning is further executed for the local graph to establish the link between the rectangular components so as to obtain the text detection result. The stable relation between the component areas is mined by utilizing depth relation reasoning, so that the detection performance of the text in any shape can be greatly improved.

Description

technical field [0001] The present invention relates to the technical field of text detection, in particular to a text detection method, device, system and storage medium based on deep relational reasoning. Background technique [0002] Scene text detection has been widely used in various applications, such as online education, product search, instant translation, and video scene parsing, etc. With the gradual development of deep learning, text detection algorithms can achieve good results in controlled environments, such as text instances with regular shapes or aspect ratios, but due to the limitations of text representations, they often cannot recognize arbitrary shapes. text. [0003] In recent years, some methods try to use connected domain strategy to solve this problem. However, these methods cannot obtain richer relationships between text components, which does not help the aggregation of text instances, and conventional convolutions are usually used in existing meth...

AI Technical Summary

Problems solved by technology

[0005] In view of the above deficiencies in the prior art, the purpose of the present invention is to provide a text detection method, device, system and storage medium based on deep relational reasoning, aiming to solve the problem of low performance of text detection with arbitrary shapes in the prior art

Images