Rahmadi Kurnia
ABSTRACT
Detection of circles in digital imagery is important in object recognition. In real life, there are many circular objects are imperfect and are blocked by other objects. In this study, the randomized circle detection method is used to detect unobstructed circle objects in a digital image. If the Hough transform method uses an accumulator to store parameter information, then randomized circle detection does not need to use accumulator. An initial stage of preprocessing is applied to reduce noise and obtain the edge of object in the image. Each object's pixel edge will be stored which will then be recognized by the randomized circle detection method and the Hough transform method. The results of these two methods are compared each other to according to three parameters: accuracy, processing time and memory storage. In this research, 110 sample images order to analyze the performance of both methods. The results showed that randomized circle detection method was more effective and efficient than Hough transform method. The randomized circle detection method can detect the circle until 20% degree of visibility. Hough transform method can detect a circle is only 40% degree of visibility. Computation time of randomized circle detection method is faster than Hough transform method and 2, 18659 seconds. The memory used randomized circle detection method smaller than HT method 128,494, 2 Kb
- Cuevas, E., Wario, F., Osuna-Enciso, V., Zaldivar, D., Pérez-Cisneros. 2012. Fast algorithm for multiple-circle detection on images using learning automata, IET Image Processing 6 (8), (2012), pp. 1124--1135.Google Scholar
- Rahmadi Kurnia, Melia Asmita, Ikhwana Elfitri. 2017. Object detection on hindered condition using chain code-based angle detection, In Proceedings of the 2017 International Conference on Telecommunications and Communication Engineering. 2017 Google ScholarDigital Library
- X. Chen, L. Lu, and Y. Gao. 2012. A new concentric circle detection method based on Hough transform, in Proceeding ofComputer Science & Education (ICCSE), 7th International Conference on Melbourne (IEEE, 2012), pp. 753--758.Google Scholar
- Jiang, Liyuan. 2013. Fast randomized algorithm for circle detection by efficient sampling. Journal of Theoretical and Applied Information Technology Vol. 48 No.2.(2103).Google Scholar
- Alomari, Yazan M,. 2014. Automatic Detection and Quantification of WBCs and RBCs Using Iterative Structured Circle Detection Algorithm. Hindawi Publishing Corporation Computational and Mathematical Methods in Medicine Volume.Google Scholar
- Suping Wu, Xiangjiao Liu. 2012 Parallelization research of circle detection based on Hough transform. IJCSI International Journal of Computer Science, Issues, Vol. 9, Issue 6, No 3, November 2012 ISSN (Online): 1694--0814Google Scholar
- Rahmadi Kurnia, Md. Altab Hossain, Akio Nakamura, Yoshinori Kuno. 2006. Generation of efficient and user-friendly queries for helper robots to detect target objects. Advanced Robotics Vol. 20. Issue5. 2006Google Scholar
- Forman, G. 2003. An extensive empirical study of feature selection metrics for text classification. J. Mach. Learn. Res. 3 (Mar. 2003), 1289--1305. Google ScholarDigital Library
- Teh-Chuan Chen, Kuo-Liang Chung. 2001. An efficient randomized algorithm for detecting circles. Computer Vision and Image Understanding. 2001 pp, 172--191. Google ScholarDigital Library
Index Terms
- Comparison of Random Circle Detection and Hough Transform Method in Detecting Obstructed Circle Object
Recommendations
Curvature aided Hough transform for circle detection
Curvature radius is adopted to improve the H-transform for circle detection.Curvature pre-estimation avoids senseless accumulation operation, work faster.The CACD is capable to detect circles of different radius in complex scene."Statistic deviation" is ...
Advanced hough transform using a multilayer fractional fourier method
The Hough transform (HT) is a commonly used technique for the identification of straight lines in an image. The Hough transform can be equivalently computed using the Radon transform (RT), by performing line detection in the frequency domain through use ...
N-Point Hough transform for line detection
In this paper, we introduce the N-point Hough transform for the detection of a large number of planar lines in a noisy image. The N-point Hough transform yields the randomized Hough transform and the three-point Hough transform if we set N=2 and N=3, ...
Comments