Binary tree-based text line accurate locating method

Abstract

The invention discloses a binary tree-based text line accurate locating method. The method comprises the steps of 1, constructing a binary tree search space for an over-segmented text line for an input natural scene image with the over-segmented text line; 2, simulating an access mode of postorder traversal in the constructed binary tree search space to search for paths, wherein each path is a node set, and the optimal path is a node set sequence obtained after all node sets are subjected to pruning and fusion operations; and 3, performing the pruning and fusion operations: for each node set contained in a path of the binary tree search space, a proper situation can be selected from eight pruning and combination policies to perform processing according to a confidence degree comparison result of a father node and left and right sub-nodes in the node set; and finally obtaining the optimal path which solves the over-segmentation problem, wherein the optimal path corresponds to a reset text line accurate locating result. According to the method, accurate locating of the text line in the scene image is realized.

Description

technical field [0001] The invention belongs to the field of scene image text line positioning, and in particular relates to a binary tree-based precise text line positioning method. Background technique [0002] Text line localization in scene images is a technique for localizing text lines in pictures taken in natural scene environments. The technology has a wide range of applications for multilingual translation, content-based web search, visual assistance, and autonomous driving. However, in the process of text line positioning, the problem of over-segmentation of text lines often occurs, that is, the area that should have been detected as a single text line, because the positioning method is not robust enough or the non-text noise in the scene image is glued to the text line. , and is divided into several incomplete parts, resulting in many false detections, making the subsequent text recognition effect poor. In addition, in order to avoid text lines tending to be und...

AI Technical Summary

Problems solved by technology

But this kind of method has the following defects: First, it does not consider the characteristics of the text line merging process, so it does not construct a data structure that meets these characteristics to represent the search space

This kind of pruning and union method with fixed threshold is inflexible and rational, and cannot efficiently search for the optimal path in the search space

Images