𝔖 Bobbio Scriptorium
✦   LIBER   ✦

Recognition invariant under unknown affine transformations of intensity

✍ Scribed by Sébastien Roy; Daniel Lefebvre; Henri H Arsenault

Publisher
Elsevier Science
Year
2004
Tongue
English
Weight
609 KB
Volume
238
Category
Article
ISSN
0030-4018

No coin nor oath required. For personal study only.

✦ Synopsis

We address the problem of image recognition in the presence of unknown uniform and nonuniform intensity transformations. Multiplicative and additive uniform intensity transformations considered are solved using a method that we recently proposed called the locally adaptive contrast-invariant filter. We now generalize this method for situations where a linear intensity gradient across an object can also be present. We use a set of four orthonormal images, and compute the correlations between each of those images and the scene, and one additional correlation and combine the five correlation planes in a nonlinear manner. Results show that discrimination is good.

📜 SIMILAR VOLUMES

Subadditive affine-invariant transformat
Subadditive affine-invariant transformations of convex bodies
✍ Guy Valette 📂 Article 📅 1974 🏛 Springer 🌐 English ⚖ 195 KB

We prove two results about the continuous maps F, from the space of d-dimensional convex bodies K of R g into the space of non-empty compact sets of R ~, which are subadditive and invariant by affine permutations. The first theorem gives properties of the images F(K). In the second one, we determine

Invariant representation, matching and p
Invariant representation, matching and pose estimation of 3D space curves under similarity transformations
✍ Stan Z. Li 📂 Article 📅 1997 🏛 Elsevier Science 🌐 English ⚖ 995 KB

This paper presents a system for matching and pose estimation of 3D space curves under the similarity transformation composed of rotation, translation and uniform scaling. The system makes use of constraints not only on the feature points but also on curve segments. A representation called the simil