AI Paper Atlas

Research map / Detection and segmentation / CNN features

On Detection of Faint Edges in Noisy Images

Nati Ofir, Meirav Galun, Sharon Alpert, Achi Brandt, Boaz Nadler, Ronen Basri

TPAMI 2019 · Detection and segmentation › CNN features · approach: Box regression and loss design · 40 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use curve detector O(N^1.5) instead of Cannyedge detection · Simulated noisy shapes, SNR 1.0-1.6F-measure: 0.57 -> 0.73Improved
use curve detector O(N^1.5) instead of Cannyedge detection · Simulated noisy shapes, SNR 1.8-2.0F-measure: 0.71 -> 0.85Improved
use curve detector O(N^1.5) instead of Cannyedge detection · Simulated noisy shapes, SNR 0.0-0.8F-measure: 0.11 -> 0.14Improved
use O(N^1.5) curves instead of faster O(N log N) curvesCurves detector · Simulated noisy shapes, SNR 1.0-1.6F-measure: 0.7 -> 0.73Improved
use curved instead of straight edge detectorOur detectors · Simulated noisy shapes, SNR 1.0-1.6F-measure: 0.63 -> 0.73Improved
use our curves instead of state-of-the-art natural image boundary detector SEedge detection · Simulated noisy shapes, SNR 1.8-2.0F-measure: 0.14 -> 0.85Improved
add BM3D denoising before CannyCanny · Simulated noisy shapes, SNR 0.0-0.8F-measure: 0.11 -> 0.04Mixed
add BM3D denoising before CannyCanny · Simulated noisy shapes, SNR 1.8-2.0F-measure: 0.71 -> 0.75Mixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy