Rapid image text detection method based on multi-channel and multi-dimensional cascade filter

Abstract

The present invention discloses a rapid image text detection method based on a multi-channel and multi-dimensional cascade filter. The problem is mainly solved that the recall ratio is low and the speed is slow in the prior art. The method comprises: 1) extracting a maximum stable extremum region in the different channels and scales of an input image as a character candidate region; 2) removing the background region in the character candidate region by employing a cascade filter from coarse to fine, namely setting a threshold value for the morphological features of the character candidate region, and performing the first grade coarse filtration; setting thresholds for the stroke width and the stroke width variable coefficient of the character candidate region, performing the second grade coarse filtration, then removing the overlapping regions, and employing a convolution neural network binary classifier perform fine filtration; and 3) aggregating the region into the character string according to the geometry and the position feature of the character candidate region after cascade filter through a graph model. The rapid image text detection method based on the multi-channel and multi-dimensional cascade filter has high recall ratio, high accuracy and fast speed, and can be used for detection of image text at various interference surroundings.

Description

technical field [0001] The invention belongs to the technical field of image processing, in particular to an image text detection method, which can be used for text detection in natural scene images such as license plates and road signs. Background technique [0002] With the rapid development of computers, handheld mobile camera devices and the popularization of web 2.0 technology, the number of network images containing text has increased dramatically. By extracting text information from images, it helps to deepen image understanding and retrieve required information from massive data, effectively saving time and improving efficiency. Traditional document text detection technology has matured, but image text still has many challenges due to its complexity, such as the variability of fonts, the complexity of the background and other interference factors. Therefore, text detection in related images has gradually become a hot spot in the field of image processing. [0003] ...

AI Technical Summary

Problems solved by technology

[0007] 1) The detection speed is slow

[0008] 2) For large characters, dot-matrix fonts, translucent and non-uniform lighting, etc., the detection performance is poor

[0009] 3) It is easy to break and lose when the string is synthesized, and the recall rate of text detection is low

Images