Method for detecting text in natural scene picture based on local width change of strokes

Abstract

The invention relates to a method for detecting text in a natural scene picture based on local width change of strokes. The method comprises the steps that 1) the natural scene picture to be detected is processed in advanced to obtain a gray scale picture, and an edge graph of the gray scale picture is obtained; 2) a corresponding binary image is generated by binarization according to the edge graph and the gray scale picture; 3) adjacent pixels of the same value are gathered to form a candidate part according to the binary image; 4) the stroke width of the candidate part is calculated to obtain the width of each pixel in stroke; 5) a filter is used to filter the candidate part according to the calculated stroke widths, and a text part is obtained by screening; and 6) the screened text parts are connected to form a text row, and a final result is displayed. The text detection method of the invention is low in calculation cost, high in efficiency and visual, and can effectively improve the text detection accuracy of the natural scene picture.

Description

technical field [0001] The invention belongs to the technical field of pattern recognition in artificial intelligence, and in particular relates to a text detection method in natural scene pictures based on partial stroke width transformation. Background technique [0002] Pictures in natural scenes refer to pictures taken directly from real scenes in life by various shooting devices such as cameras, mobile phones, etc., without specific restrictions. It is necessary to find text areas in natural scene images. These text data carry very useful and important information in people's daily life, such as street signs, billboards, traffic signs, etc., which are very helpful for assisting people to obtain scene information. . The appearance of text is mainly to remind people to pay attention to some useful information. Using portable devices around us to extract, identify and record, and even search for relevant content online can greatly facilitate our lives. Text is the most d...

AI Technical Summary

Problems solved by technology

The principle of the method based on the connected domain is relatively intuitive, and it is only suitable for processing images with a relatively simple background; the basic idea of ​​the method based on the texture analysis is to consider the text area as a special texture object, and its detection accuracy is high, but it needs to be processed on the entire image. Scanning and texture segmentation requires a lot of training in advance, the calculation cost is relatively high, and the detection effect is also related to the training samples; the edge-based method is prone to high false alarms, so how to effectively filter the background edge requires more follow-up processing

Images