Edge detection method based on fractional-order signal processing
A fractional order and detection method technology, applied in the field of image processing, can solve problems affecting detection accuracy and achieve the effect of filtering out false edges
Inactive Publication Date: 2013-07-24
HANGZHOU HENGSHENG ELECTRONICS TECH +4
View PDF0 Cites 1 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
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
[0031] The present invention will be further described in detail below in conjunction with the accompanying drawings.
[0032] The invention proposes an image edge detection method based on fractional order signal processing. As we all know, image edge detection is generally obtained by calculating the gradient information of the target pixel, which is analogous to the extreme value operation in the function. The extreme value operation often brings unnecessary noise interference, so the Canny method uses Gaussian smoothing preprocessing to eliminate the noise effect as much as possible, but this will affect the accuracy of edge detection. How to make a compromise between noise resistance and detection accuracy has always been a difficult point. To solve this problem, we propose an edge detection algorithm based on fractional order signal processing. We do not perform noise smoothing preprocessing on the image before the gradient calculation, so it will not have any impact o...
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 an edge detection method based on fractional-order signal processing, aiming at solving edge detection which is a traditional trouble in the pattern recognition field. The method is a novel algorithm which can conduct gradient operation to all target pixel points in an image by using the fractional-order signal processing to obtain an edge, and comprises that a gray-level matrix is generated from any image, the gradient operation is conducted respectively to each pixel point in the matrix by adopting detection operators to obtain the gradient amplitude of each pixel point, then non-maximum value suppression is conducted to the gradient image and finally a double-threshold method is adopted for judging whether the target pixel points are edge points and are connected with the edge or not. The invention omits the process of smooth filtering preprocessing conducted to the image and utilizes a novel derivative algorithm based on the fractional-order signal processing to conduct the gradient operation. Fractional integrals in the algorithm can suppress the interference introduced during derivation. The entire method has the advantages that the signal-to-noise ratio is good, the edge positioning is accurate and the false edge can be effectively suppressed. The algorithm can be used in the fields such as the automatic target recognition and the like.
Description
technical field [0001] The invention belongs to the field of image processing, and relates to an edge detection method, in particular to an image edge detection method based on fractional order signal processing. Background technique [0002] Image threshold segmentation is a widely used image processing technology, which can usually be used for edge detection and segmentation of images. The current threshold segmentation processing is generally based on gray value calculation. This method first determines a gray value change gradient threshold in the gray value range of the image, and then calculates the gray value change gradient of each pixel in the image. Compared with this threshold, and according to the comparison result, the corresponding pixel points are classified into two categories that are larger than the threshold or smaller than the threshold, and further distinguish whether the pixel is an edge point. [0003] In the classic threshold image method, a threshol...
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): H04N5/14H04N5/202
Inventor 叶永强潘祥杨海波姜斌周大可
Owner HANGZHOU HENGSHENG ELECTRONICS TECH