Author:
Nakashima Shota, ,Miyauchi Makoto,Serikawa Seiichi,
Abstract
Arbitrary figure extraction, a basic image processing problem, is done typically using the generalized Hough transform (GHT). GHT and its successors tend, however, to consume humongous amounts of processing time and memory space. The arbitrary figure extraction we propose using one-dimensional histograms takes advantage of the Polytope method, which features: (1) The histogram distribution changes if parameters representing figures change. (2) Optimum parameters are obtained, if the value of the highest-frequency histogram becomes maximum. This approach makes memory space very small, processing time very short, effective by extracts arbitrary curves with different aspect ratios, and the algorithm is simple.
Publisher
Fuji Technology Press Ltd.
Subject
Artificial Intelligence,Computer Vision and Pattern Recognition,Human-Computer Interaction
Reference12 articles.
1. M. Saji, A. Ueno, H. Takeda, “A Robot System to Recognize and Manage Unfixable Objects in the Office Environment,” IEICE technical report, Vol.99, No.717, pp. 1-8, 2000.
2. D.H. Ballard, “Generalizing the Hough transform to detect arbitrary shapes,” Pattern Recognition, Vol.13, No.2, pp. 111-122, 1981.
3. R.O. Duda and P.E. Hart, “Use of the Hough transformation to detect lines and curves in pictures,” Commun. ACM, Vol.15, No.1, pp. 11-15, 1972.
4. P.-F. Fung, W.-S. Lee, and I. King, “Randomized generalized Hough transform for 2-D gray scale object detection,” Pattern Recognition, Vol.2, pp. 511-515, 1996.
5. C. F. Olson, “Improving the generalized Hough transform through imperfect grouping,” Image and Vision Computing, Vol.16, No.9-10, pp. 627-634, 1998.
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献