Method for extracting text information from adaptive images

Abstract

The invention discloses a method for extracting text information from adaptive images, and relates to technology for extracting text information from images. The method comprises the following steps: 1) preprocessing the images; 2) analyzing complexities of the backgrounds of the images; 3) initially detecting texts; 4) verifying the texts; 5) extracting the texts; and 6) outputting or displaying the text information. The method adopts different text detection methods for the images with different complexities of the backgrounds by computing the complexities of the backgrounds of the images, reduces missing and false detection caused by a single text detection method, and improves the overall performance of a text extracting system. The computation method of the complexities of the backgrounds of the images is simple and effective. The method can detect text information in the images with different complexities of the backgrounds, and the text information detected by the method is free from the influence of type-font, word size and language; and the method has strong commonality.

Description

technical field [0001] The invention relates to the technical field of text information extraction in the field of pattern recognition and machine vision, in particular to an adaptive image text information extraction method. Background technique [0002] With the wide application of image acquisition equipment such as digital cameras, cameras, and ultra-high-speed scanners, the information in images has attracted more and more attention. However, it is still difficult for computers to understand the content of images. The text embedded in the image can provide some important information that people want, such as the cover of the book, the video, the color picture of the natural scenery picture www web page, etc., which is of great help to understand the content in the image. Let the computer recognize the text in the image like a human, that is, the automatic detection system of the text has attracted more and more attention in recent years. It has extremely important signi...

AI Technical Summary

Problems solved by technology

[0005] The above-mentioned existing research methods, the edge-based text extraction method is simple to calculate, but due to the use of a single edge detection method, the detection effect is not ideal when the contrast between the text and the background is not much different; , it is also easy to get wrong results

This requires the combination of other information to expand the detection range; Texture-based text extraction methods need to extract effective texture features, although it can effectively detect the area where the text is located, it will also extract background areas with similar textures, which need to be combined with other Features; the main difficulty of the color-based clustering method is that it is impossible to predict the color of the text and background, so it is difficult to determine the number of color subgraphs. Too many or too few clusters will affect the extraction performance, and the calculation is very large; The methods based on connected regions cannot be used alone in most cases, and are generally used after edge, texture and color methods

[0006] When the above methods extract text information, the complexity of the image background and the contrast between the text and the background are not considered. For images with different background complexity, a single extraction method is used, which is easy to miss some texts with weak contrast. area or wrongly extract the text-like area, resulting in poor overall extraction effect

Images