Relative gradient operator improves edge detection under brightness changes

From the Superderivative to a Relative-Gradient Edge Operator

Computer Vision and Pattern Recognition

Summary

Edge detectors usually look for absolute changes in brightness to find edges in images, but this can be affected if the whole image gets brighter or darker. The authors revisit an operator called the log-gradient which measures relative changes in brightness, making it more stable when the overall brightness changes. They explain the math behind it, show how to compute it efficiently, and compare its performance to classic edge detectors on benchmark images. Although the relative operator isn’t the absolute best in all tests, it offers an important property of brightness invariance and slightly improves detection in some settings.

What this means in practice

  • For computer vision engineers: Improve edge detection algorithms in changing lighting by incorporating relative-gradient calculations for more consistent feature extraction.
  • For medical image analysts: Enhance visibility of edges in medical scans that vary in brightness due to different imaging conditions using relative-gradient edge operators.

Authors

Alejandro Garnung Menéndez

Abstract

First-derivative edge detectors such as Sobel, Prewitt, Roberts and Scharr measure absolute grey-level differences. We revisit the log-gradient magnitude, a relative-gradient edge operator, and motivate it by analogy with the superderivative, a multiplicative derivative in which the independent variable is perturbed multiplicatively rather than additively. In one and two dimensions the logarithm of the superderivative is a radial logarithmic derivative; its local, origin-free, isotropic analogue is the magnitude of the logarithmic gradient. The resulting operator measures relative rather than absolute change, giving an edge-strength map that is invariant under global intensity rescaling. We present the theory, show how the operator can be implemented in two steps---a classical gradient kernel plus a pointwise division---and compare it with standard first-derivative filters on synthetic images with ground-truth edges and on the official BSDS500 benchmark. We also study a parametric family that interpolates between the absolute gradient and the log-gradient; empirically, the best members are small intermediate exponents, which edge the classical kernels by a small but statistically detectable margin in the per-image metric and, with the same Gaussian smoothing as the single-$σ$ Canny, match it in ODS and lead it in OIS and AP, while the tuned Canny remains ahead in ODS. The single-threshold margin over the kernels does not replicate on the held-out test split, and the fully relative endpoint is never the best member, its ranking depending on the edge-map normalisation. The contribution is the construction and the invariance it buys, not a new state of the art.