Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A natural scene image and text detection technology, applied in image analysis, image data processing, character and pattern recognition, etc., can solve problems such as complex lighting and large impact on text detection, and achieve good robustness
Inactive Publication Date: 2009-05-20
HARBIN INST OF TECH
View PDF0 Cites 10 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
[0004] The present invention provides a natural scene image text detection method in order to solve the problems of complex illumination and large impact of text and background contrast changes on text detection in texture-based text detection methods
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 more
Image
Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
specific Embodiment approach 1
[0013] Specific implementation mode one: see figure 1 , this embodiment consists of the following steps:
[0014] Step 1, first obtain the image resource, which can be an image file in any image format, such as bmp, jpg, gif or tiff, etc. The source of the image file can be the image resource provided on the Internet, a special image library or personal collection of image data ;
[0015] Step 2, through the formula:
[0016] LHBP k ( x c , y c ) = Σ p = 0 7 ( f k ( x p , y p ) - ...
specific Embodiment approach 2
[0022] Specific embodiment two, this embodiment further defines the multi-scale tropism analysis method described in step three on the basis of specific embodiment one, which consists of the following steps:
[0023] Step A1, use the m×n detection window template to slide on the LHBP image in sequence on the corresponding scale, and count the four directions of horizontal, vertical, diagonal, and anti-diagonal lines in the current window according to the LHBP tropism texture coding table The number of pixels on the window, judge whether the number of pixels in any two or more of the above four directions reaches the corresponding threshold at the same time, if the judgment result is yes, then mark the area corresponding to the window as the candidate text area , the judgment result is no, then re-execute step A1 to continue sliding judgment;
[0024] Step A2, classify the candidate text regions through the support vector machine based on the LHBP histogram, and finally determi...
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 image characters in natural scene and relates to a method for adopting a texture descriptor LHBP to describe the texture character of an image and adopting a multi-dimension tropistic wave filtering method to detect characters in the image, thereby solving the problem that the character detection method based on texture has complex requirement on illumination; and the change of contrast gradient between the character and the background has great influence on detection. The obtained LHBP tropistic texture code and the corresponding code produced according to the change of position weight are obtained; a character region is determined through a multi-dimension tropistic analytic method. The method adopts a mode of extracting local texture on multi-dimension wavelet character by the LHBP texture descriptor, can filter out the influence of complexity and the change situation of the contrast ratio between the character and the background, effectively extracts the texture character of the character region, utilizes the texture direction property of the character region to determine the final character region and has good robustness in complex illumination, the change of the contrast gradient between the character and the background, the change of the size and the stroke thickness of the character and the like.
Description
technical field [0001] The invention belongs to the technical category of image processing and understanding, and uses a texture descriptor LHBP to describe image texture features and adopts a multi-scale tropism filtering method to detect text in images. Background technique [0002] The development of multimedia technology has promoted the growth of multimedia data represented by images and videos. In order to effectively browse and manage multimedia data, content-based multimedia access and content understanding is a major technical challenge that needs to be solved urgently. The text detection algorithm for visual scenes is of great significance to the semantic understanding of multimedia. [0003] At present, there are mainly three types of text detection methods in images: edge-based, connected component analysis-based and texture-based methods. The method based on edge features uses the characteristics of more edges in the text area to classify and screen text blocks...
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
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.