AI Paper Atlas

Research map / Image generation / Image restoration

Image Projective Invariants

Erbo Li, Hanlin Mo, Dong Xu, Hua Li

TPAMI 2018 · Image generation › Image restoration · approach: Image harmonization and color transformation · 20 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 projective weighted moment invariants instead of affine moment invariantsPIs · Flavia leaf classificationaccuracy: 60.75% -> 72.83%Improved
use PIs instead of Hu momentsPIs · Flavia leaf classificationaccuracy: 36.25% -> 72.83%Improved
use PIs instead of Zernike and Gaussian-Hermite momentsPIs · Flavia leaf classificationaccuracy: 34.42% and 27.83% -> 72.83%Improved
use PIs instead of AMIsretrieval features · COIL-20wrong retrievals in top 72: 41 -> 6Improved
use PIs instead of other moment invariantsretrieval features · synthetic butterfly databaseprecision-recallImproved
use Gaussian derivative filters instead of least squares to estimate image partial derivatives (ablation)PIs · USC-SIPI imagesaverage relative errorImproved
normalize moments by number of nonzero pixels (ablation)PIs · USC-SIPI imagescalculation errorImproved

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