Using Graphics Hardware for Enhancing Edge and Circle Detection

Authors:
Antonio Ruiz;Manuel Ujaldón;Nicolás Guil
Affiliations:
Computer Architecture Department, University of Malaga, 29071 Málaga, Spain;Computer Architecture Department, University of Malaga, 29071 Málaga, Spain;Computer Architecture Department, University of Malaga, 29071 Málaga, Spain
Venue:
IbPRIA '07 Proceedings of the 3rd Iberian conference on Pattern Recognition and Image Analysis, Part II
Year:
2007

Citing 7
Cited 2

A Computational Approach to Edge Detection

IEEE Transactions on Pattern Analysis and Machine Intelligence
Digital image processing

Digital image processing
Pipelined implementation of the multiresolution Hough transform in a pyramid multiprocessor

Pattern Recognition Letters
A Parallel Pipelined Hough Transform

Euro-Par '96 Proceedings of the Second International Euro-Par Conference on Parallel Processing-Volume II
A Graphics Hardware Implementation of the Generalized Hough Transform for fast Object Recognition, Scale, and 3D Pose Detection

ICIAP '03 Proceedings of the 12th International Conference on Image Analysis and Processing
OpenVIDIA: parallel GPU computer vision

Proceedings of the 13th annual ACM international conference on Multimedia
An improved constant-time algorithm for computing the Radon and Hough transforms on a reconfigurable mesh

IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans

On the computation of the Circle Hough Transform by a GPU rasterizer

Pattern Recognition Letters
High Performance Circle Detection through a GPU Rasterization Approach

IbPRIA '09 Proceedings of the 4th Iberian Conference on Pattern Recognition and Image Analysis

Quantified Score

Hi-index	0.00

Visualization

Abstract

A broad family of problems in computer vision and image analysis require edge and circle detection. This paper explores the properties of the Hough transform for such tasks, improving them under a novel implementation on commodity graphics hardware. We demonstrate both a faster execution and a more reliable detection under different scenarios and a range of parameters selection. Overall, a consistent 3-6 acceleration factor and beyond is achieved for a 500 MHz GeForce 7950 GX2 graphics card versus a typical 3 GHz Pentium 4 dual-core CPU.