A sub-pixel circle detection algorithm combined with improved RHT and fitting
- PDF / 3,163,309 Bytes
- 19 Pages / 439.37 x 666.142 pts Page_size
- 66 Downloads / 270 Views
A sub-pixel circle detection algorithm combined with improved RHT and fitting Guojun Wang 1 Received: 18 December 2019 / Revised: 30 June 2020 / Accepted: 31 July 2020 # Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract
Circle extraction is usually a pre-completed task used in different applications related to medical, robotics, biometrics image analysis among others. Randomized Hough Transform (RHT) determines the parameters of the circle by randomly obtaining three edge pixels, if they are not precisely located on the circumference. The detected circle will not perfectly match the ideal circle. At the same time, three random points are largely not on a circle, which leads to some invalid sampling and parameter accumulation. In this paper, an improved RHT combined with fitting subpixel circle detection algorithm is proposed. The improved RHT algorithm calculates and accumulates parameters by using 1 point obtained from random sampling and another two points obtained from horizontal and vertical search respectively. The algorithm introduces the edge map of the de-soliton point and small region, and improves the probability that three points belong to the same circle. Then, the set of edge pixels corresponding to the identified circle is fitted to reduce the bias effect caused by only using three edge pixels to calculate the circle parameters. In this way, the reliability of the fitting and the precision of the parameters are improved while removing the noise. Experimental tests were conducted for detection performance, accuracy of parameter estimation and noise robustness. Compared with other methods, the proposed method has strong anti-interference ability and high calculation accuracy. Keywords Bias effect . Invalid sampling . Subpixel . RHT . Circle detection
1 Introduction Circle detection is a key problem in pattern recognition and computer vision [1, 10]. For example, face matching, gaze estimation rely largely on an accurate iris localization [30]. In traffic signs, on the other hand, circular markers have been used for autonomous navigation
* Guojun Wang [email protected]
1
Field Engineering College, Army Engineering University of PLA , Nanjing 21007, China
Multimedia Tools and Applications
tasks [21]. Similar applications observation on laser serve as reference points [27] for visionbased deflection measurement. In advanced integrated circuit packing, the detection of the circular holes [22] on flexible printed circuits’(FPC) surfaces through machine vision is very useful to identify root causes in FPC manufacturing process. In extrinsic calibration of widelyseparated cameras, multi-cue-based method for detecting circular regions [17] provides accurate calibration results. Given the relevance to this problem, different methods for circle detection have been investigated in order to offer a solution. Evolutionary and swarm-based algorithms are widely used because of their effectiveness. For example, circle detectors have been proposed using the learning automata [8], the ele
Data Loading...
