Contextual performance prediction for low-level image analysis algorithms

Autor: M. Prenat, Christine Graffigne, M. Roux, B. Chalmond

Publikováno v: IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. 10(7)

This paper explores a generic approach to predict the output accuracy of an algorithm without running it, by a careful examination of the local context. Such a performance prediction will allow one to qualify the appropriateness of an algorithm to tr

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5de7e087932a9326c7b16123049b8fd8
https://pubmed.ncbi.nlm.nih.gov/18249677

Ultrasound Backscatter characterization by using Markov random field model

Autor: Christine Graffigne, Nizar Bouhlel, Meriem Jaidane, Sylvie Sevestre-Ghalila

Publikováno v: ICASSP2006
IEEE International Conference on Acoustics, Speech and Signal Processing
IEEE International Conference on Acoustics, Speech and Signal Processing, May 2006, Toulouse, France. pp.1124-1127
Scopus-Elsevier
IEEE International Conference on Acoustics, Speech and Signal Processing, May 2006, Toulouse, France. 2, pp.1124-1127, 2006
HAL
ICASSP (2)

International audience; This paper evaluates a K-Markov random field model for retrieving information about backscatter characteristics, especially regularity spacing scatterers in simulated ultrasound image. The model combines a statistical K-distri

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c8d4b403c7f1ee1846b3902bf771c47d
https://hal.archives-ouvertes.fr/hal-00173925/document

3D Biological object detection and labeling in multidimensional microscopy imaging

Autor: Christine Graffigne, Alain Trubuil, Juhui Wang

Publikováno v: 11. ICIAP
11. ICIAP, 2001, Palermo, Italy
CIAP 2001
International Conference on Image Analysis and Processing (ICIAP 2001)
International Conference on Image Analysis and Processing (ICIAP 2001), 2001, Palermo, Italy. pp.215-220, 2001
International Conference on Image Analysis and Processing (ICIAP 2001), 2001, Palermo, Italy. pp.215-220
HAL
ICIAP
Conférence ICIP 2002
Conférence ICIP 2002, 2002, Rochester, United States

One essential assumption used in object detection and labeling by imaging is that the photometric properties of the object are homogeneous. This homogeneity requirement is often violated in microscopy imaging. Classical methods are usually of high co

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4c5b6cb4b66232cce6136b5180279568
https://hal.inrae.fr/hal-02761269

Deep seafloor characterization with multibeam echosounders by image segmentation using angular acoustic variations

Autor: Christine Graffigne, Jean-Marie Augustin, Samantha Dugelay

Publikováno v: SPIE Proceedings.

The new generation of low-frequency echosounders, primarily used for bathymetric purposes, are also able to record acoustic images of the sea floor. Reflected energy, as a function of the incidence angle, is known to be strongly dependent on seabed t

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::9e85917569a07928b7c6db98e77edb26
https://doi.org/10.1117/12.253450

Hierarchical method for the detection of moving objects in a sequence of images

Autor: Wei Xiong, Christine Graffigne

Publikováno v: Neural, Morphological, and Stochastic Methods in Image and Signal Processing.

In this paper, a hierarchical version of the segmentation of motion with Markov field is used in order to detect moving objects in two successive images. We use the same hierarchical method which guarantees convergence for the initialization of the s

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::0a3075fb7e323d52cbcea7d2bb3b7312
https://doi.org/10.1117/12.216366