A Method for Detecting Text Areas in Images
An image and text technology, applied in the field of detection of text areas in images, can solve the problems of inapplicable detection methods and large interference of text areas in images, etc., and achieve the effect of easy processing and application
Active Publication Date: 2019-07-02
HANGZHOU ZHUOJIAN INFORMATION TECH CO LTD
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0006] However, for an image with a complex background, because the complex background has a lot of interference on the text area in the image, the above-mentioned existing detection methods for the text area in the image are not applicable
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0032] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are the Some, but not all, embodiments are invented.
[0033] Such as figure 1 As shown, this embodiment discloses a method for detecting a text region in an image, which may include the following steps 101-105:
[0034] 101. Divide an image into multiple sub-images, where there is no overlapping area between the multiple sub-images and the multiple sub-images constitute the image.
[0035] In this embodiment, in step 101, the image may be divided into multiple sub-images with the same size. For example, each sub-image is 9×9.
[0036] 102. Determine the text confidence of each sub-image based on a preset character recognition ...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a method for detecting a text area in an image, comprising: dividing an image into a plurality of sub-images, wherein there is no overlapping area between the plurality of sub-images and the plurality of sub-images constitute the image; character recognition based on preset rule, determine the text confidence of each sub-image; based on the text confidence of each sub-image and the preset text confidence threshold, determine the target connected domain, and the target connected domain is used to determine each text region contained in the image ; Based on a preset connected domain determination rule, determine each connected domain included in the image; based on each connected domain included in the image and the target connected domain, determine each text region included in the image. Compared with the prior art, the detection method of the text area in the image proposed by the present invention locates the text area in the image with a relatively complex background by dividing the image into multiple sub-images and determining the text confidence of each sub-image, which is suitable for Images with complex backgrounds.
Description
technical field [0001] The invention relates to the technical field of image processing, in particular to a method for detecting text regions in an image. Background technique [0002] Currently, the commonly used detection methods for text regions in images include methods based on connected domains, methods based on edge features and methods based on texture features. The specific description of each method is as follows: [0003] Based on the method of connected domain, assuming that the characters in the same area have similar color and brightness, and there is a large difference in color from the background area, a bottom-up method is used to extract the connected area from the image, and then use geometric constraints to construct Heuristic rules are used to analyze connected domains, and the sub-regions are merged to obtain the final text region. [0004] The method based on the edge feature is to use the feature that the text area has rich edge information to detec...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00
CPCG06V30/413
Inventor 刘立刘艳洋吴诗展
Owner HANGZHOU ZHUOJIAN INFORMATION TECH CO LTD