A Method of Improving the Speed of Random Circle Detection in Specific Situations
A technology for detecting speed and random circles, which is applied to computer components, instruments, calculations, etc., and can solve the problems of large calculation and storage requirements
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
experiment example 1
[0058] figure 2 (a) is an image with a size of 200 pixels × 200 pixels, such as figure 2 As shown in (a), there are 5 circles in the graph, and there are 647 edge points on these 5 circles. now to figure 2 In (a), different degrees of random noise are added sequentially, and the noise ratio is 50% to 300%, that is, the number of added noise points is 324 to 1941. figure 2 (b) is to figure 2 The image obtained after adding 1618 noise points in (a). Applying RHT, RCD and the algorithm of this paper respectively figure 2 The image after adding noise in (a) is used for circle detection. The detection time consumed by these three algorithms is shown in Table 1. Using the algorithm of this paper to figure 2 (b) 100 times of detection are carried out, and the coordinates and radius of each circle center can be accurately obtained. From the 100 times of detection, the randomly selected detection results are shown in Table 2 and figure 2 (c), where figure 2 The origin ...
experiment example 2
[0066] image 3 (a) is an image with a size of 250 pixels × 250 pixels. There are 4 circles (3 of which are incomplete), a straight line, a rectangle and two ellipses in the picture, with a total of 1170 edge points . now to image 3 In (a), different degrees of random noise are added sequentially, and the noise ratio is 40% to 200%, that is, the number of added noise points is 468 to 2340. image 3 (b) is to image 3 The image obtained after adding 2340 noise points in (a). Applying RHT, RCD and the algorithm of this paper respectively image 3 The image after adding noise in (a) is used for circle detection. The detection time consumed by these three algorithms is shown in Table 4. Using the algorithm of this paper to image 3 (b) Perform 100 tests, and the coordinates and radius of each circle center can be obtained accurately. From these 100 tests, the randomly selected test results are shown in Table 5 and image 3 (c) shown. Use the algorithm of this paper to i...
experiment example 3
[0075] Figure 4 (a) is an actual image with a size of 140 pixels×140 pixels, and there are 4 circles in this image. The circle detection process is as Figure 4 shown, where the edge image Figure 4 There are a total of 1688 edge points in (b). Using RHT, RCD and the algorithm of this paper to Figure 4 (b) Circle detection takes 5.4185 seconds, 2.1138 seconds and 0.4958 seconds respectively. In the process of 50 detections, the three algorithms can correctly extract the center coordinates and radius of each circle (the detection results of the algorithm in this paper are as follows: Figure 4 As shown in (c), the average values of p1, c1, r1, r1 / p1, p2, c2, r2, r2 / p2 in this algorithm are 765.88, 561.76, 1.04, 0.001358, 2128706, 16487.58, 2.96, 0.000001 .
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More