Randomized Circle Detection Research Articles

A fast and accurate circle detection algorithm based on random sampling

Circle detection in digital images is an important problem in computer vision, pattern recognition, and artificial intelligence. However, the common circle detection strategies, including random sample consensus, randomized Hough transform, and randomized circle detection, have a very low sampling efficiency and thus a slow detection speed, owing to aimless random sampling. This paper proposes a fast and accurate randomized circle detection algorithm, with the aim to improve the speed and accuracy of circle detection based on random sampling. The proposed algorithm mainly focuses on four aspects: calculating circle parameters, determining candidate circles, searching for true circle, and improving detection accuracy. To verify the effectiveness of our algorithm, contrastive experiments were conducted on lots of synthetic and real images. The results show that our algorithm achieved much higher detection speed and accuracy than random sample consensus, randomized Hough transform, and randomized circle detection, and realized similar robustness as the three contrastive strategies. The research ideas can also be applied to ellipse detection.

A mobile vision testing application based on dynamic distance determination from the human corneal limbus.

Here we present a mobile application that accurately determines the distance between an optical sensor and the human corneal limbus for visual acuity assessment. The application uses digital image processing and randomized circle detection to locate the cornea. Then, a reference scaling measurement is employed to calculate distance from the sensor to a user. To determine accuracy and generalizability, testing was conducted both with 200 static images, 25 images each of males and females for four ethnic groups from a facial image database, and live image streams from a test subject. Average absolute corneal radius error over 10 trials for the static images was 6.36%, while average absolute distance error for the live image streams was less than 1%. Subsequently, distance measurements were used to scale letter sizes for a Snellen Chart-based visual acuity assessment. This system enables monitoring of chronic retinal diseases, as patients can quickly and accurately measure their visual acuity through the mobile eye exam suite.

Bullet Impact Detection in Silhouettes Using Mask R-CNN

The bullet impact detection in the silhouette plays an important role in the institutions which have a shooting range, specially where are regulated the license to carry a gun and where the evaluation manual process could present distortion in the ability’s evaluation of the shooter and like a consequence the license’s issuance. This paper proposes a method for an automatic detection of the bullet impacts in silhouettes based on deep learning and image processing, which consist of the following steps: pre-processing, impacts detection, edge detection and evaluation results. The experiments about 600 silhouettes with 2401 bullet impacts images of the proposed and implemented method considering the models Resnet 50 and Resnet 101 for Mask R-CNN show that Resnet 50 get better results than Resnet 101, achieving 97.6 %, 99.5 %, and 97.9 %, of accuracy, precision and recall, respectively, above the methods Circular Hough Transform, Circlet Detection, Random Sample Consensus, Randomized Hough Transform, Randomized Circle Detection, Support Vector Machine, Faster R-CNN, MnasNet and YOLO. Also, the results show 100 % of effectiveness in the edge detection and the count of the detected bullet impacts.

Monitoring of Volume of Air in Inhalation From Triflo Using Video Processing

Breathing exercise training with a flow-oriented incentive spirometer (or Triflo) is important in lung expansion rehabilitation for patients with lung surgery or pulmonary injury. In this article, we propose a novel technique to estimate the volume of air inhaled and the sustained inhalation time based on video processing. The proposed technique combines a randomized circle detection algorithm to detect the three balls in Triflo tubes and a normalized cross-correlation algorithm to track these three balls that rise due to inhalation. The values of inhalation and the sustained inhalation time intervals are automatically recorded as screenshots on a personal computer for later analysis by a doctor. Three major experiments were conducted to verify the advantages of this proposed system. The first experiment evaluated the performances of both the ball detection and the tracking algorithms showing 3.68% error. The second experiment applied the proposed method implemented, so that it displays in plots the changes in the inhalation rate, as the training of a postoperative volunteer progressed. In the last experiment, a healthy subject employs Triflo to test the inhalation training format for lung volume regeneration with three levels of difficulty, to record the number of successful breathing maneuvers. When the data are displayed in rate versus time plots, a graph can help a doctor to appropriately plan the training program for the benefit of patients, because a more adaptable therapy can be realized and varying degrees of difficulty can be implemented. In addition, the patients can comfortably practice in home-based rehabilitation, seeing the improvements in the inspiratory muscle performance in computer screenshots.

A Surface Defect Detection Framework for Glass Bottle Bottom Using Visual Attention Model and Wavelet Transform

Glass bottles must be thoroughly inspected before they are used for packaging. However, the vision inspection of bottle bottoms for defects remains a challenging task in quality control due to inaccurate localization, the difficulty in detecting defects in the texture region, and the intrinsically nonuniform brightness across the central panel. To overcome these problems, we propose a surface defect detection framework, which is composed of three main parts. First, a new localization method named entropy rate superpixel circle detection (ERSCD), which combines least-squares circle detection and entropy rate superpixel (ERS) with an improved randomized circle detection, is proposed to accurately obtain the region of interest (ROI) of the bottle bottom. Then, according to the structure-property, the ROI is divided into two measurement regions: central panel region and annular texture region. For the former, a defect detection method named frequency-tuned anisotropic diffusion super-pixel segmentation (FTADSP) that integrates frequency-tuned salient region detection (FT), anisotropic diffusion, and an improved superpixel segmentation is proposed to precisely detect the regions and boundaries of defects. For the latter, a defect detection strategy called wavelet transform multiscale filtering (WTMF) based on a wavelet transform and a multiscale filtering algorithm is proposed to reduce the influence of texture and to improve the robustness to localization error. The proposed framework is tested on four data sets obtained by our designed vision system. The experimental results demonstrate that our framework achieves the best performance compared with many traditional methods.

An Improved Randomized Circle Detection Algorithm Using in Printed Circuit Board Locating Mark

This paper presents an improved Randomized Circle Detection (RCD) algorithm with the characteristic of circularity to detect randomized circle in images with complex background, which is not based on the Hough Transform. The experimental results denote that this algorithm can locate the circular mark of Printed Circuit Board (PCB).

Circular hole detection algorithm based on image block

Circular hole detection is a common problem in computer vision and pattern recognition. Randomized Hough transform and randomized circle detection algorithm are commonly used in circle detection, with good detection robustness and accuracy. But for circular holes with smaller radius, the two algorithms will be too slow because of a large number of invalid sampling. Thus the circular hole detection algorithm based on image block is proposed in order to improve the speed of circular hole detection. The algorithm divides the image into several small blocks and 3 points from the same block are randomly selected for sampling each time. If a candidate circular hole can be obtained by calculating these 3 points, then the points in the 4 blocks (or less) closest to the center of the candidate hole will be used for evidence-collecting to determine whether the candidate circular hole is true. Experimental results on a large number of synthetic images and real images show that the detection speed of circular hole detection algorithm proposed is much faster than the speed of randomized Hough transform and randomized circle detection algorithm. In addition, the proposed algorithm has the same detection robustness and accuracy as the randomized circle detection algorithm. The block strategy proposed in this paper is also applicable to the detection of elliptical holes.

Fast circle detection algorithm based on sampling from difference area

The detection of circular targets is a basic problem in computer vision, especially in pattern recognition. Due to the low effective sampling rate, circle detection methods based on random sampling (like randomized Hough transform and randomized circle detection algorithm) result in heavy computation load and slow detection speed. Targeted at this problem, this paper proposes a fast circle detection algorithm based on the difference area sampling. When a candidate circle is determined to be a false circle, a number of samples are taken from its difference area if the number of points on the candidate circle reaches a certain number. And the sampling efficiency in the difference area is significantly higher than that of the random sampling, thus increasing the speed of the circle detection. A large number of experimental results also validate this advantage. The proposed algorithm has the same detection accuracy and robustness as the original algorithm, and the proposed method of sampling from the difference area boasts great potential in practical application as it can be directly applied to randomized Hough transform, randomized circle detection algorithm and their improved versions.

A fast and robust circle detection method using isosceles triangles sampling

Circle detection using randomized sampling has been developed in recent years to reduce computational intensity. However, randomized sampling is sensitive to noise that can lead to reduced accuracy and false-positive candidates. To improve on the robustness of randomized circle detection under noisy conditions this paper presents a new methodology for circle detection based upon randomized isosceles triangles sampling. It is shown that the geometrical property of isosceles triangles provides a robust criterion to find relevant edge pixels which, in turn, offers an efficient means to estimate the centers and radii of circles. For best efficiency, the estimated results given by the sampling from individual connected components of the edge map were analyzed using a simple clustering approach. To further improve on the accuracy we applied a two-step refinement process using chords and linear error compensation with gradient information of the edge pixels. Extensive experiments using both synthetic and real images have been performed. The results are compared to leading state-of-the-art algorithms and it is shown that the proposed methodology has a number of advantages: it is efficient in finding circles with a low number of iterations, it has high rejection rate of false-positive circle candidates, and it has high robustness against noise. All this makes it adaptive and useful in many vision applications.

Ball detection in soccer images using isophote’s curvature and discriminative features

Ball recognition in soccer matches is a critical issue for automatic soccer video analysis. Unfortunately, because of the difficulty in solving the problem, many efforts of numerous researchers have still not produced fully satisfactory results in terms of accuracy. This paper proposes a ball recognition approach that introduces a double level of innovation. Firstly, a randomized circle detection approach based on the local curvature information of the isophotes is used to identify the edge pixels belonging to the ball boundaries. Then, ball candidates are validated by a learning framework formulated into a three-layered model based on a variation of the conventional local binary pattern approach. Experimental results were obtained on a significant set of real soccer images, acquired under challenging lighting conditions during Italian "Serie A" matches. The results have been also favorably compared with the leading state-of-the-art methods.

Randomized circle detection with isophotes curvature analysis

Circle detection is a critical issue in image analysis and object detection. Although Hough transform based solvers are largely used, randomized approaches, based on the iterative sampling of the edge pixels, are object of research in order to provide solutions less computationally expensive. This work presents a randomized iterative work-flow, which exploits geometrical properties of isophotes in the image to select the most meaningful edge pixels and to classify them in subsets of equal isophote curvature. The analysis of candidate circles is then performed with a kernel density estimation based voting strategy, followed by a refinement algorithm based on linear error compensation. The method has been applied to a set of real images on which it has also been compared with two leading state of the art approaches and Hough transform based solutions. The achieved results show how, discarding up to 57% of unnecessary edge pixels, it is able to accurately detect circles within a limited number of iterations, maintaining a sub-pixel accuracy even in the presence of high level of noise.

Efficient sampling strategy and refinement strategy for randomized circle detection

Circle detection is fundamental in pattern recognition and computer vision. The randomized approach has received much attention for its computational benefit when compared with the Hough transform. In this paper, a multiple-evidence-based sampling strategy is proposed to speed up the randomized approach. Next, an efficient refinement strategy is proposed to improve the accuracy. Based on different kinds of ten test images, experimental results demonstrate the computation-saving and accuracy effects when plugging the proposed strategies into three existing circle detection methods.

Alleviating the computational load of the probabilistic algorithms for circles detection using the connectivity represented by graph

The probabilistic algorithms are effective and widely used to recognize the curves in machine vision and image processing. In this paper, a novel algorithm for detecting circles is presented. It is based on the observation that the connectivity can help to alleviate the computational load of the probabilistic algorithm. A graph model is introduced to express connectivity in the detected edges, and a modified depth-first-search algorithm is developed to segment the whole graph into connected subgraphs and then partition the complex subgraph into simple paths. Then, four pixels are randomly selected from the sampling set, consisting of one proper path or several consecutive paths, to detect circles. The connectivity constraint is further employed to verify the candidates of circles to eliminate the pseudo ones. The experiments, comparing the proposed algorithm with the randomized Hough transform and the efficient randomized circle detection algorithm, show that it has the advantages of computational efficiency and robustness.