Image segmentation method and system based on fuzzy control and computer storage medium

Abstract

The application discloses a kind of based on fuzzy control's image segmentation method, system and computer storage medium, method includes: determining fuzzy controller type;According to the fuzzy controller type setting fuzzy reasoning;According to the result of the fuzzy reasoning, defuzzification is carried out, obtains final threshold value;According to the final threshold value, threshold segmentation is carried out, and result image is obtained.The application sets two different threshold values by fuzzy control algorithm, when image is segmented under different illumination environments, gray is uniform and stable, and the applicability is strong, without manual adjustment, and efficiency is high.

Description

Technical Field

[0001] This invention relates to the field of image processing technology, and in particular to an image segmentation method, system, and computer storage medium based on fuzzy control. Background Technology

[0002] Thresholding segmentation is a region-based image segmentation technique. It works by setting different thresholds to classify image pixels into several categories based on their grayscale levels. However, under varying natural lighting conditions (day or night, sunny or rainy, seasonal), the grayscale of the captured image can become uneven. Since thresholding typically requires two threshold parameters (upper and lower), both need to be determined manually using prior knowledge or through trial and error. Interference from natural light or the light source itself can affect subsequent image segmentation, thus impacting the segmentation results. Currently, the main methods to prevent this are manually adjusting the light source and continuously changing the threshold. However, this method suffers from poor stability, limited applicability, and low efficiency. Summary of the Invention

[0003] The present invention provides an image segmentation method, system and computer storage medium based on fuzzy control to solve the problems of poor stability, weak applicability and low efficiency of the existing region-based threshold segmentation method.

[0004] On one hand, embodiments of the present invention provide an image segmentation method based on fuzzy control, including:

[0005] Determine the type of fuzzy controller;

[0006] Set up fuzzy inference according to the fuzzy controller type;

[0007] Defuzzification is performed based on the result of the fuzzy inference to obtain the final threshold.

[0008] Threshold segmentation is performed based on the final threshold to obtain the resulting image.

[0009] In one possible implementation, the fuzzy controller type is a one-input, two-output fuzzy controller.

[0010] In one possible implementation, the step of defuzzifying based on the result of the fuzzy inference to obtain the final threshold includes: defuzzifying using the maximum average method.

[0011] On the other hand, embodiments of the present invention provide an image segmentation system based on fuzzy control, comprising:

[0012] The fuzzy control selection module is used to determine the type of fuzzy controller;

[0013] The logic setting module is used to set fuzzy inference according to the fuzzy controller type;

[0014] The defuzzing module is used to defuzzify the result of the fuzzy inference to obtain the final threshold.

[0015] The image processing module is used to perform threshold segmentation based on the final threshold to obtain the result image.

[0016] On the other hand, embodiments of the present invention provide a computer storage medium storing a plurality of computer instructions, which are used to cause a computer to execute the above-described method.

[0017] The image segmentation method, system, and computer storage medium based on fuzzy control disclosed in this invention have the following advantages:

[0018] This invention uses a fuzzy control algorithm to set two different thresholds, resulting in uniform and stable grayscale when segmenting images under different lighting conditions. It has strong applicability, requires no manual adjustment, and is highly efficient. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a schematic diagram of an image segmentation method based on fuzzy control provided in an embodiment of the present invention;

[0021] Figure 2 A threshold 1 membership function graph of an image segmentation method based on fuzzy control provided in an embodiment of the present invention;

[0022] Figure 3 A threshold-2 membership function graph of an image segmentation method based on fuzzy control provided in an embodiment of the present invention;

[0023] Figure 4 The illumination intensity membership function graph is provided for an image segmentation method based on fuzzy control in an embodiment of the present invention. Detailed Implementation

[0024] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0025] Figure 1 This is a schematic diagram of an image segmentation method based on fuzzy control provided by an embodiment of the present invention. The embodiment of the present invention provides an image segmentation method based on fuzzy control, comprising:

[0026] Determine the type of fuzzy controller;

[0027] Set up fuzzy inference according to the fuzzy controller type;

[0028] Defuzzification is performed based on the result of the fuzzy inference to obtain the final threshold.

[0029] Threshold segmentation is performed based on the final threshold to obtain the resulting image.

[0030] For example, setting fuzzy inference according to the fuzzy controller type involves defining input and output fuzzy sets. First, the input and output fuzzy sets are determined. The input is the light intensity, and the output is a low threshold and a high threshold. The light intensity fuzzy set is: D (dark), SL (slightly bright), L (bright), DL (very bright), LL (extremely bright). The low threshold fuzzy set is: SD (small), MD (medium), LD (large). The high threshold fuzzy set is: NG (small), MG (medium), LG (large).

[0031] The input and output membership functions are redefined as shown in formulas v1, v2, and v3.

[0032]

[0033] Where v1 is the light intensity membership function, v2 is the threshold 1 membership function, and v3 is the threshold 2 membership function. The threshold 1 membership function graph is shown below. Figure 2 As shown, the membership function graph for threshold 2 is as follows: Figure 3 The graph of the light intensity membership function is shown below. Figure 4 As shown in Table 1, the brightness range is set to 0–60, and the grayscale value is set to 0–255. Then, based on the fuzzy set definition, fuzzy rules are used to obtain the fuzzy control table.

[0034] Table 1

[0035] D SD NG SL SD MG L MD MG DL MD LG LL LD LG

[0036] The light intensity includes: D (dark), SL (slightly bright), L (bright), DL (very bright), LL (extremely bright), with the low threshold being threshold 1, including: SD (small), MD (medium), LD (large), and the high threshold being threshold 2, including: NG (small), MG (medium), LG (large).

[0037] The fuzzy inference is then set as follows. (Where z represents light intensity, and x and y represent threshold 1 and threshold 2, respectively.)

[0038] IF z is D, THEN x is SD and y is NG.

[0039] IF z is SL, THEN x is SD and y is MG.

[0040] IF z is L, THEN x is MD and y is MG.

[0041] IF z is DL, THEN x is MD and y is LG.

[0042] IF z is LL, THEN x is LD and y is LG.

[0043] Next, the maximum average method is used for deblurring to obtain precise thresholds 1 and 2. Since the difference between thresholds 1 and 2 is always 'a', threshold 1 - 'a' needs to be assigned as the final threshold. Finally, image segmentation is performed on the grayscale of image pixels according to the obtained final thresholds. For example, if the natural light brightness is 30, and the light source is normal and there is no natural light, a threshold of 50 and 100 is set for an image, with a difference a = 50. From a certain moment onwards, due to the weather clearing up (or daylight or summer), the surrounding environment becomes brighter, and the light source is greatly affected by natural light factors, causing the average grayscale value of the image captured by the camera to increase. When the brightness reaches 50, according to the membership function formula V1, it can be seen that... Therefore make From formulas V2 and V3, we get V1 = V2 = 192. Therefore, we set the new threshold 1 and new threshold 2 to 142 and 192, respectively. The opposite occurs when the weather turns cloudy (or darkens or it's winter).

[0044] In one possible embodiment, the fuzzy controller type is a one-input, two-output fuzzy controller.

[0045] For example, the fuzzy controller with one input and two outputs has light intensity as the input and low threshold and high threshold as the output.

[0046] This invention provides an image segmentation system based on fuzzy control, comprising:

[0047] The fuzzy control selection module is used to determine the type of fuzzy controller;

[0048] The logic setting module is used to set fuzzy inference according to the fuzzy controller type;

[0049] The defuzzing module is used to defuzzify the result of the fuzzy inference to obtain the final threshold.

[0050] The image processing module is used to perform threshold segmentation based on the final threshold to obtain the result image.

[0051] This invention provides a computer storage medium storing a plurality of computer instructions, which are used to cause a computer to execute the above-described method.

[0052] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0053] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. An image segmentation method based on fuzzy control, characterized in that, include: The illumination intensity corresponding to the image is obtained as the input to the fuzzy controller; A fuzzy controller with one input and two outputs is adopted, with the light intensity as the input and low threshold and high threshold as the output. The fuzzy set of the illumination intensity is defined as D, SL, L, DL, LL, where D represents dark, SL represents slightly bright, L represents bright, DL represents very bright, and LL represents extremely bright. The fuzzy set of the low threshold is defined as SD, MD, and LD, where SD represents small, MD represents medium, and LD represents large. The fuzzy set of the high threshold is defined as NG, MG, and LG, where NG represents small, MG represents medium, and LG represents large. Based on the following fuzzy rules, fuzzy reasoning is performed on the illumination intensity to obtain the membership degrees of the low and high thresholds: When the light intensity is D, the low threshold is SD and the high threshold is NG; When the light intensity is SL, the low threshold is SD and the high threshold is MG; When the light intensity is L, the low threshold is MD and the high threshold is MG; When the light intensity is DL, the low threshold is MD and the high threshold is LG; When the light intensity is LL, the low threshold is LD and the high threshold is LG; The membership degrees of the low and high thresholds are defuzzified using the maximum average method to obtain the corresponding threshold 1 and threshold 2, wherein the difference between threshold 1 and threshold 2 is a preset constant a. The final segmentation threshold is obtained by subtracting the preset constant a from the threshold 1; The image pixels are thresholded based on the final segmentation threshold to obtain the resulting image.

2. An image segmentation system based on fuzzy control, characterized in that, The system is applied to the method of claim 1, comprising: The fuzzy control selection module is used to determine the type of fuzzy controller; The logic setting module is used to set fuzzy inference according to the fuzzy controller type; The defuzzing module is used to defuzzify the result of the fuzzy inference to obtain the final threshold. The image processing module is used to perform threshold segmentation based on the final threshold to obtain the result image.

3. A computer storage medium, characterized in that, The computer storage medium stores a plurality of computer instructions, which are used to cause the computer to execute the method of claim 1.

Images