English text detection method with text direction correction function

Abstract

The invention belongs to the technical field of image processing, and specifically relates to an English text detection method with a text direction correction function. The method comprises the following steps of: respectively carrying out maximally stable extremal region detection on each channel of an English text image so as to obtain candidate text regions; establishing a convolutional neuralnetwork model-based classifier, and filtering wrong candidate text regions so as to obtain preliminary text regions; grouping the preliminary text regions by utilizing a double-layer text grouping algorithm; and carrying out direction correction on the grouped preliminary text regions so as to obtain a corrected text. According to the method, an enhanced multichannel MSER model is utilized to obtain more refined text regions, a parallel SPP-CNN classifier is imported to better distinguish text regions and non-text regions, images with any sizes can be processed, and pool features can be extracted under multiple scales, so that more features can be known through multilayer space information of source images; and the method is capable of processing slightly inclined scene texts.

Description

technical field [0001] The invention belongs to the technical field of image processing, in particular to an English text detection method with text direction correction. Background technique [0002] Text in natural scene images has accurate and rich information, which is of great significance for image analysis, image-based translation, image search, etc. Over the past 20 years, researchers have proposed several methods for detecting text in images of natural scenes. There are many content-based multimedia understanding applications such as automatic visual classification, image retrieval, assisted navigation, multilingual translation, object recognition, and consumer-oriented applications. [0003] The key problems faced by scene text detection are: (1) Texts in document images have regular fonts, similar colors, uniform size and uniform arrangement, but even in the same scene, texts in natural scenes may have different fonts, colors , scale and orientation. (2) The ba...

AI Technical Summary

Problems solved by technology

[0003] The key problems faced by scene text detection are: (1) Texts in document images have regular fonts, similar colors, uniform size and uniform arrangement, but even in the same scene, texts in natural scenes may have different fonts, colors , scale and orientation

(2) The background of natural scene images may be very complex

[0007] These methods distinguish text areas from non-text areas according to the rules or characteristics that distinguish text areas from non-text areas. Although these methods can detect text, they lack the correction of English text and the discrimination effect on italic text. Not good, the recognized text has severe separation due to the slant of the words

Images