- 【Updated on May 12, 2025】 Integration of CiNii Dissertations and CiNii Books into CiNii Research
- Trial version of CiNii Research Knowledge Graph Search feature is available on CiNii Labs
- 【Updated on June 30, 2025】Suspension and deletion of data provided by Nikkei BP
- Regarding the recording of “Research Data” and “Evidence Data”
A High-Resolution Variable Hough Transform using LoG Filter
-
- Morimoto Masashi
- NTT
-
- Suenaga Yasuhito
- NTT
Bibliographic Information
- Other Title
-
- LoGフィルタを用いた高精度可変Hough変換
Search this article
Description
The ability of line extraction from a image by the Hough Transform is strongly affected by the quantization error of the image and the Hough space.We have proposed a new method ″Vaxiable Hough Transform(VHT)″ to improve the extraction ability.In VHT,2D- distributed voting is performed by using a Variable Filter.This paper proposes a Laplacian-of-Gaussian filter as the optimum Variable Filter.This filter is constructed from the frequency analysis of the Hough space by Radon Transform and Fourier Transform.The lower bound and the optimum filter size is calculated from the analysis and the mathmatical analysis. Experiments show that the filter can improve the ability and the accuracy better than usual Hough Transform and previous VHTs.
Journal
-
- IEICE technical report. Pattern recognition and understanding
-
IEICE technical report. Pattern recognition and understanding 93 (134), 1-8, 1993-07-09
The Institute of Electronics, Information and Communication Engineers
- Tweet
Keywords
Details 詳細情報について
-
- CRID
- 1570854177362784512
-
- NII Article ID
- 110003299682
-
- NII Book ID
- AN10013232
-
- Text Lang
- ja
-
- Data Source
-
- CiNii Articles