An Extension to Hough Transform Based on Gradient Orientation

TL;DR

This paper introduces a novel extension to the Hough transform that integrates gradient orientation and accumulator space extension, improving line detection accuracy and reducing clutter in applications like visual inspection.

Contribution

The paper presents a new method combining gradient orientation with an extended accumulator space to enhance line detection performance.

Findings

Improved peak prominence in line detection

Reduced clutter in the Hough space

Enhanced performance in visual inspection tasks

Abstract

The Hough transform is one of the most common methods for line detection. In this paper we propose a novel extension of the regular Hough transform. The proposed extension combines the extension of the accumulator space and the local gradient orientation resulting in clutter reduction and yielding more prominent peaks, thus enabling better line identification. We demonstrate benefits in applications such as visual quality inspection and rectangle detection.