A fast detection method for text in complex background based on interactive platform
A complex background and interactive platform technology, applied in the field of rapid text detection in complex backgrounds, can solve the problems of slow text positioning speed, and achieve the effect of fast text positioning, low requirements, and simple calculation complexity
Active Publication Date: 2019-05-10
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF7 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0007] The purpose of the present invention is to overcome the deficiencies of the prior art, to provide a fast detection method for text in complex backgrounds based on an interactive platform, which solves the problem of too slow text positioning speed, and can quickly locate the text in the picture, and has a relatively fast detection method. strong robustness
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
[0074] Describe technical scheme of the present invention in further detail below in conjunction with accompanying drawing: as figure 1 As shown, a fast detection method for text in complex background based on an interactive platform, which includes the following steps:
[0075] S1: Input image preprocessing: perform preprocessing operations on the input image to enhance the contrast of text edges;
[0076] This step first converts the color image collected by the camera into a grayscale image, because the response of the image to the light in the grayscale space is not very obvious. Then use two image processing methods to preprocess the image:
[0077] Described step S1 comprises the following sub-steps:
[0078] S11: Perform histogram averaging on the input image, so that the gray histogram of the original image changes from a relatively concentrated gray-scale interval to a uniform distribution in the entire gray-scale range, the formula is as follows:
[0079]
[00...
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 quickly detecting text in a complex background based on an interactive platform, which includes the following steps: S1: input image preprocessing; S2: fast positioning of text candidate regions: performing contour detection on the image preprocessed in step S1 , and use a rectangular frame to select each closed area, and then use the SIFT algorithm to quickly locate all corner points in each rectangular frame, and use the number of corner points as a preliminary screening condition for preliminary screening; S3: through the normalization algorithm first Adjust the image to a uniform size, and then project the content of the original image to the center of the normalized image through the forward mapping method, and correct the angle appropriately; S4: Text / background screening: first extract features, The candidate regions filtered by the trained classifier are the detected text regions. The invention realizes the text detection in the complex background, and the main problem it solves is how to quickly locate the horizontal text and the text with the rotation angle in the image under the condition of maintaining high precision.
Description
technical field [0001] The invention relates to the fields of computer vision and human-computer interaction, in particular to a rapid detection method for text in complex backgrounds based on an interactive platform. Background technique [0002] The problem of text detection in complex backgrounds is regarded as a classic problem in both the field of computer vision and the field of human-computer interaction. There are two reasons. First, this technology has a wide range of applications. For example, this technology can be used to allow smart devices such as mobile phones to read books for us, or it can be applied to unmanned vehicles to allow vehicles to automatically recognize road signs. Secondly, the text detection problem is sometimes very difficult to solve, because text detection is different from general target detection such as faces, vehicles, and pedestrians. The shape of the text is more changeable (various degrees of deformation and blurring often appear), ...
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): G06K9/00G06K9/62
CPCG06V30/414G06F18/24
Inventor 程洪王光甫杨路
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA