Results 251 to 260 of about 11,872,577 (297)

Kronecker Decomposition for Image Classification

2016
We propose an image decomposition technique that captures the structure of a scene. An image is decomposed into a matrix that represents the adjacency between the elements of the image and their distance. Images decomposed this way are then classified using a maximum margin regression (MMR) approach where the normal vector of the separating hyperplane ...
Sabrina Fontanella, Antonio Jose Rodríguez-Sánchez, Justus H. Piater, Sándor Szedmák   +3 more
openaire   +2 more sources

Nuclear image sequence decomposition

COMPSAC 79. Proceedings. Computer Software and The IEEE Computer Society's Third International Applications Conference, 1979., 2005
This research concerns the problem of dis criminating between various radioactive objects on the basis of their differing dynamics (photon intensity as a function of time) in a sequence of images. Each object is assumed to be homogeneous dynamically, but to differ in intensity from point to point.
Earl E. Cose, William H. Rose, W. Earl Barnes, Ervin Kaplan, James S. Arnold   +4 more
openaire   +1 more source

Image Decomposition Application to SAR Images

2003
We construct an algorithm to split an image into a sum u + v of a bounded variation component and a component containing the textures and the noise. This decomposition is inspired from arecent work of Y. Meyer. We find this decomposition by minimizing a convex functional which depends on the two variables u and v, alternatively in each variable.
Aujol, Jean-François, Aubert, Gilles, Blanc-Féraud, Laure, Chambolle, Antonin   +3 more
openaire   +3 more sources

Image compression by the wavelet decomposition

European Transactions on Telecommunications, 1992
AbstractDecomposition of images with the Haar orthonormal basis which is an important member of compactly supported Wavelets and a quadtree structured hierarchical coding technique are used in this work to obtain high image compression efficiency and time complexity linear in the number of pixels.
Maria Grazia Albanesi, I. De Lotto, L. Carrioli   +2 more
openaire   +1 more source

Intrinsic Image Decomposition by Pursuing Reflectance Image

Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, 2022
Intrinsic image decomposition is a fundamental problem for many computer vision applications. While recent deep learning based methods have achieved very promising results on the synthetic densely labeled datasets, the results on the real-world dataset are still far from human level performance.
Tzu-Heng Lin, Pengxiao Wang, Yizhou Wang 0001   +2 more
openaire   +1 more source

Intrinsic Decompositions for Image Editing

Computer Graphics Forum, 2017
Intrinsic images are a mid-level representation of an image that decompose the image into reflectance and illumination layers. The reflectance layer captures the color/texture of surfaces in the scene, while the illumination layer captures shading effects caused by interactions between scene illumination and surface geometry.
Nicolas Bonneel, Balazs Kovacs, Sylvain Paris, Kavita Bala   +3 more
openaire   +1 more source

Intrinsic decomposition for stereoscopic images

2016 IEEE International Conference on Image Processing (ICIP), 2016
Intrinsic image decomposition is an important technique that decomposes an image into reflectance and shading components. In this paper, we enable intrinsic decomposition for stereoscopic images. Traditional approaches cannot be directly applied to decompose stereoscopic images, yielding inconsistent reflectance and 3D artifacts after recoloring.
Dehua Xie, Shuaicheng Liu, Kaimo Lin, Shuyuan Zhu, Bing Zeng 0001   +4 more
openaire   +2 more sources

Image decomposition using deconvolution

2010 IEEE International Conference on Image Processing, 2010
We present a novel method for decomposing an image into base and texture layers. Our method is simple and effective, and can handle textures of high contrast, which traditional image filtering techniques may not handle efficiently. The method first removes high-frequency texture information using low-pass filtering, and then restores structural ...
Sunghyun Cho, Hyunjun Lee, Seungyong Lee 0001   +2 more
openaire   +1 more source

Sparse Representations for Image Decompositions

International Journal of Computer Vision, 1999
We are given an image I and a library of templates {\cal L} , such that {\cal L} is an overcomplete basis for I. The templates can represent objects, faces, features, analytical functions, or be single pixel templates (canonical templates). There are infinitely many ways to decompose I as a linear combination of the library templates.
Davi Geiger, Tyng-Luh Liu, Michael J. Donahue   +2 more
openaire   +1 more source

A hierarchical morphological image decomposition

Pattern Recognition Letters, 1990
Abstract This paper presents a new hierarchical image description based on a morphological skeleton representation. The primitives of this representation are size scaled versions of well defined primitive shapes (structuring elements). The construction of the skeleton itself and the determination of the hierarchical relation between its components ...
openaire   +2 more sources