Scene text end-to-end identification method based on boundary point detection

Abstract

The invention discloses a scene text end-to-end recognition method based on boundary point detection, and the method comprises the steps: extracting text features through a feature pyramid network, and generating candidate textboxes through a region extraction network; detecting a more accurate multi-directional bounding box of the text instance through a multi-directional rectangular detection network; secondly, detecting an upper boundary point sequence and a lower boundary point sequence of the text in the multi-directional bounding box; and finally, converting the text in any shape into ahorizontal text by utilizing the detected boundary point sequence for the subsequent attention mechanism-based sequence recognition network to performing recognizing, and finally, finding out the mostmatched word of the prediction sequence in the given dictionary by utilizing a cluster search algorithm to obtain a final text recognition result. According to the method, the scene text in any shapein the natural image can be detected and recognized at the same time under the condition that character-level labeling is not needed, the scene text comprises the horizontal text, the multi-directiontext and the curved text, and end-to-end training can be completely carried out.

Description

technical field [0001] The invention belongs to the technical field of computer vision, and more specifically relates to an end-to-end recognition method for scene text based on boundary point detection. Background technique [0002] In the field of computer vision, scene text detection and recognition is a very active and challenging research direction, and many practical applications are highly related to it, such as network information security monitoring systems, intelligent transportation systems, and assistance for the blind. [0003] In most of the past studies, scene text detection and recognition techniques are regarded as two separate processes, that is, the first step uses a trained detector to detect text regions in natural scene pictures, and the second step uses the first step The detected text area is input into the recognition module for recognition, and the text content is obtained. Since detection and recognition tasks are highly related and complementary ...

AI Technical Summary

Problems solved by technology

However, such methods require character-level annotation, and the recognition network cannot model text sequence information

Images