Structural light stripe edge extraction method based on curvelet transformation
A curvelet transform and edge extraction technology, applied in the field of image processing, can solve the problems of reducing the image matting effect and reducing the integrity, and achieve the effect of improving the matting effect and ensuring the integrity.
Inactive Publication Date: 2022-06-14
苏州兴喜博信息技术科技有限公司
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0002] When cutting out the image on the picture, the edge line of the image is usually determined first. After the edge line of the image is determined, the selected image is cut out, and the selected image is cut out, and the edge line of the image is determined. When it is determined, in order to obtain the accurate edge line of the image, the curvelet transformation will be performed on the entire image to obtain the edge line of the image, and when using the curvelet transform to extract the edge line of the entire image, in order to make the extracted edge The smooth connection of the line will curve the position where the edge line has a large angle to ensure the smoothness of the image edge line. For the smoothness of the edge line, the image content at the small edge of the image will be ignored, thereby reducing the image from the image. Buckle out of the integrity, reducing the effect of image matting
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 1
[0038] see figure 1 As shown, the purpose of this embodiment is to provide a method for extracting the edge of structured light lines based on curvelet transform, including the following steps:
[0039] S1, perform picture segmentation on the picture, divide the picture into several small pictures, distinguish the divided small pictures, and select the small pictures with the edge of the picture;
[0040] The specific steps of S1 are as follows:
[0041] S11, read the picture, determine the general outline of the image edge in the picture, and mark and display the determined image edge outline;
[0042] S12, using a picture segmentation algorithm to perform picture segmentation on the picture that needs edge extraction, and dividing the picture into several small pictures, and after the picture segmentation is completed, the segmented small pictures are sequentially numbered;
[0043] When performing image segmentation, the two-dimensional otsu algorithm in the image segment...
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 relates to the technical field of image processing, in particular to a structured light stripe edge extraction method based on curvelet transformation. The method comprises the following steps of performing picture segmentation on a picture, analyzing image edges in small pictures by applying curvelet transformation, performing edge enhancement on extracted edge points, sorting and placing the small pictures of which edge lines are detected according to serial numbers of the small pictures, and connecting the edge lines on each small picture and performing extraction. According to the method, the picture is divided into a plurality of small pictures, the image edge points on the small pictures are obtained through curvelet change, the edge points are enhanced, the enhanced edge points are subjected to gray scale change, the edge points are subtracted or compensated, the edge points are sequentially connected, details at the corners of the image are described, and the edge points of the image are extracted. The determined boundary line can retain the details of the image so as to ensure the completeness of the cut-out image and improve the image matting effect.
Description
technical field [0001] The invention relates to the technical field of image processing, in particular to a method for extracting the edge of structured light lines based on curvelet transformation. Background technique [0002] When the image on the picture is cut out, the edge line of the image is usually determined first. After the edge line of the image is determined, the selected image is cut out, the selected image is cut out, and the edge line of the image is cut out. When it is determined, in order to obtain the accurate edge line of the image, the entire image will be subjected to curvelet transformation to obtain the edge line of the image. The smooth connection of the line will curve the position where the edge line has a larger angle to ensure the smoothness of the image edge line. In order to smooth the edge line, the image content at the small edge of the image will be ignored, thereby reducing the image from the picture. The integrity of the deduction is redu...
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 Applications(China)
IPC IPC(8): G06T7/13G06T7/12G06T7/181G06K9/62G06V10/764
CPCG06T7/13G06T7/12G06T7/181G06T2207/20076G06T2207/20192G06T2207/10004G06T2207/20021G06F18/2321
Inventor 申兴琭丁晓喜王兴博
Owner 苏州兴喜博信息技术科技有限公司