Improvement of Harris algorithm based on Gaussian scale space

Abstract EN

Features is the description of the image contents which could be corner, blob or edge.

Corners are one of the most important feature to describe image, therefore there are many algorithms to detect corners such as Harris, FAST, SUSAN, etc.

Harris is a method for corner detection and it is an efficient and accurate feature detection method.

Harris corner detection is rotation invariant but it isn’t scale invariant.

This paper presents an efficient harris corner detector invariant to scale, this improvement done by using gaussian function with different scales.

The experimental results illustrate that it is very useful to use Gaussian linear equation to deal with harris weakness.