CN111986111A - An image segmentation method - Google Patents

Abstract

The invention discloses an image segmentation method, comprising the following steps: S1: separating all pixel points of an image to be segmented, and inserting a pixel demarcation point between each adjacent two pixel points; S2: sequentially according to the setting Scan the pixel demarcation point with a certain scanning path; S3: When scanning each pixel demarcation point, obtain the pixel value of each pixel point around the pixel demarcation point, and analyze the adjacent two pixel points around the pixel demarcation point. Compare the pixel values of the pixel values; S4: Obtain the pixel demarcation point around the pixel demarcation point, and scan the pixel demarcation points around the pixel demarcation point; S5: Connect all the reserved coordinates into a line, and perform the image processing according to the line. segmentation. The present invention obtains a point that can be divided by scanning, scans around the adjacent division point to obtain adjacent division points, and finally connects all division points, that is, the division point to be divided can be obtained. Image.

Description

An image segmentation method

technical field

The invention relates to the field of image processing, in particular to an image segmentation method.

Background technique

Image segmentation is a technique and process of identifying specific and unique regions and proposing objects of interest. It is a key step from image processing to image analysis. In the current image segmentation, whether the five points are divided into one image or multiple images, the image to be segmented will be scanned as a whole, and finally the image to be segmented can be obtained. operation, which makes the image segmentation time longer.

SUMMARY OF THE INVENTION

The purpose of the present invention is to overcome the problems existing in the above-mentioned prior art, and provide an image segmentation method, which can obtain a point that can be divided by scanning, and scan the adjacent surrounding of the divided point, so that a similar point is obtained. The adjacent segmentation points, and finally all the segmentation points are connected, that is, the image to be segmented can be obtained.

To this end, the present invention provides an image segmentation method, comprising the following steps:

S1: Separate all the pixels of the image to be segmented, and insert a pixel demarcation point between every two adjacent pixel points, so that each pixel demarcation point is surrounded by the pixels of the image, and obtain all the pixel points of the image. The coordinates of the pixel demarcation point.

S2: Scan the pixel boundary points sequentially according to the set scanning path.

S3: When scanning each pixel demarcation point, obtain the pixel value of each pixel point around the pixel demarcation point, and compare the pixel values of two adjacent pixel points around the pixel demarcation point. When the difference between the pixel values of the two pixel points is greater than the set value, the coordinates of the pixel boundary point are reserved and the process goes to step S4; otherwise, the process goes to step S2.

S4: Acquire the pixel boundary point around the pixel boundary point, scan the pixel boundary point around the pixel boundary point, and perform step S3 until the coordinates of the pixel boundary point that are retained again are the coordinates of the pixel boundary point.

S5: Connect all the reserved coordinates into a line, segment the image according to the line, and finally remove all pixel boundary points in the image.

Further, in step S2, the initial scanning position is the position where any pixel demarcation point is located.

Further, the set path is a spiral path.

Further, in step S1, when the coordinates of the pixel boundary points are obtained, coordinates are uniformly allocated to all the pixel boundary points. Among the coordinates of the adjacent two pixel boundary points, the absolute difference between the abscissa or the difference between the ordinates is The value is 1.

Further, before step S1, denoising is performed on the image to be processed.

An image segmentation method provided by the present invention has the following beneficial effects: obtaining a segmentable point by scanning, scanning around the adjacent segmentation point to obtain adjacent segmentation points, and finally in the Connect all the segmentation points to get the image to be segmented.

Description of drawings

FIG. 1 is a schematic block diagram of the overall flow of the present invention.

Detailed ways

A specific embodiment of the present invention will be described in detail below with reference to the accompanying drawings, but it should be understood that the protection scope of the present invention is not limited by the specific embodiment.

In this application document, the component models and structures that are not specified are the prior art known to those skilled in the art, and those skilled in the art can set it according to the needs of the actual situation. No specific restrictions are made.

Specifically, as shown in FIG. 1, an embodiment of the present invention provides an image segmentation method, including the following steps:

S1: Separate all the pixels of the image to be segmented, and insert a pixel demarcation point between every two adjacent pixel points, so that each pixel demarcation point is surrounded by the pixels of the image, and obtain all the pixel points of the image. The coordinates of the pixel demarcation point.

In this step, a pixel demarcation point is inserted between two adjacent pixel points using the point insertion algorithm. After traversing each pixel point of the image, a new image can be obtained. In the new image, there are no two There is a pixel boundary point between adjacent pixels, so that each pixel point is surrounded by adjacent pixel boundary points, each pixel point will be adjacent to a pixel boundary point, and each pixel boundary point will be adjacent a pixel.

S2: Scan the pixel boundary points sequentially according to the set scanning path.

In this step, the scanning path may use an S-shaped path or a spiral path. In short, the path needs to traverse to each pixel boundary point. The best way to traverse pixel segmentation points is to use an S-shaped path, because the S-shaped path can traverse every pixel segmentation point, and each pixel segmentation point is scanned only once.

S3: When scanning each pixel demarcation point, obtain the pixel value of each pixel point around the pixel demarcation point, and compare the pixel values of two adjacent pixel points around the pixel demarcation point. When the difference between the pixel values of the two pixel points is greater than the set value, the coordinates of the pixel boundary point are reserved and the process goes to step S4; otherwise, the process goes to step S2.

In this step, the values of the pixels around the pixel boundary point are judged, and whether the boundary point of the pixel point is at the image dividing line where the image can be divided is judged according to the difference of the pixel values of the surrounding pixel points. When the difference between the pixel values of the pixel points is greater than the set value, it is considered that the boundary point of the pixel point is the image dividing line where the image can be divided. If not, proceed to step S2 to scan the next pixel boundary point.

S4: Acquire the pixel boundary point around the pixel boundary point, scan the pixel boundary point around the pixel boundary point, and perform step S3 until the coordinates of the pixel boundary point that are retained again are the coordinates of the pixel boundary point.

In this step, when a pixel demarcation point has been obtained as a qualified pixel demarcation point, the adjacent pixel demarcation points around it are scanned, so that along one of the pixel demarcation points that meet the requirements, the pixel demarcation point can be quickly obtained. Other qualified pixel demarcation points.

S5: Connect all the reserved coordinates into a line, segment the image according to the line, and finally remove all pixel boundary points in the image.

In this step, the coordinates of all the reserved pixel point boundary points are connected into a line, which is the image segmentation line. According to the segmentation line, the segmented image can be obtained. Finally, all the pixel boundary points in the image are divided After removal, the original image segmented image is obtained.

In this embodiment, in step S2, the initial scanning position is the position where any pixel boundary point is located. This scheme is suitable for spiral paths, which can greatly reduce the number of operations, while for S-shaped paths, it is recommended to scan from the corner vertices of the image.

Meanwhile, in this embodiment, the set path is a spiral path. When the spiral path is used, it is possible to avoid repeating the traversal of the pixel boundary points that have been performed in step S4 when performing step S4, which can save the operation steps when the image is segmented, thereby improving image segmentation. s efficiency.

In this embodiment, in step S1, when obtaining the coordinates of the pixel boundary points, coordinates are uniformly allocated to all pixel boundary points. Among the coordinates of two adjacent pixel boundary points, the difference between the abscissas or the ordinate is The absolute value of the difference is 1. In this way, the coordinates between the boundary points of two adjacent pixels have no gaps and jumps. When the coordinates are summarized later, the obtained image segmentation line is smoother, and the function of the obtained image segmentation line will also be better. Precise.

In this embodiment, before step S1, denoising processing is performed on the image to be processed. Through the denoised image, the pixel values between adjacent pixels are smoother, and the error will be smaller when the pixel values are compared.

The above disclosures are only a few specific embodiments of the present invention, however, the embodiments of the present invention are not limited thereto, and any changes that can be conceived by those skilled in the art should fall within the protection scope of the present invention.

Claims (5)

1. an image segmentation method, is characterized in that, comprises the steps: S1: Separate all the pixels of the image to be segmented, and insert a pixel demarcation point between every two adjacent pixel points, so that each pixel demarcation point is surrounded by the pixels of the image, and obtain all the pixel points of the image. the coordinates of the pixel demarcation point; S2: Scan pixel boundary points in turn according to the set scanning path; S3: When scanning each pixel demarcation point, obtain the pixel value of each pixel point around the pixel demarcation point, and compare the pixel values of two adjacent pixel points around the pixel demarcation point. When the difference between the pixel values of the two pixel points is greater than the set value, the coordinates of the pixel boundary point are reserved and go to step S4, otherwise, go to step S2; S4: obtain the pixel demarcation point around the pixel demarcation point, and scan the pixel demarcation point around the pixel demarcation point, and perform step S3, until the coordinates of the pixel demarcation point retained again are the coordinates of the pixel demarcation point; S5: Connect all the reserved coordinates into a line, segment the image according to the line, and finally remove all pixel boundary points in the image. 2 . An image segmentation method according to claim 1 , wherein, in step S2 , the initial scanning position is the position where any pixel boundary point is located. 3 . 3. An image segmentation method according to claim 2, wherein the set path is a spiral path. 4. a kind of image segmentation method as claimed in claim 1, is characterized in that, in step S1, when obtaining the coordinates of pixel demarcation point, uniformly assign coordinates for all pixel demarcation points, adjacent two pixels In the coordinates of the boundary point, the absolute value of the difference between the abscissas or the difference between the ordinates is 1. 5 . The image segmentation method according to claim 1 , wherein, before step S1 , denoising is performed on the image to be processed. 6 .

Images