[SSC] Seminar #2 x2 with Dr. Majid Mirmehdi

[mortazavi at ce.sharif.edu]

hi everyone,

we're going to have a busy day on 15th of Mordad as SSC introduces :

2 Seminar's with the title's of:

1- CACE: A Charged Active Contour based on Electrostatics
2- Quality Inspection of Ceramic Tiles: Color Histograms and
Texture Exemplars

by Dr. Majid Mirmehdi

join us at Sunday 15th of Mordad 2PM, Khawrazmi Hall


First Talk:
Title:
CACE: A Charged Active Contour based on Electrostatics

Abstract:
We propose a novel active contour model by incorporating particle
based electrostatic interactions into the geometric active contour
framework. The proposed active contour, embedded in level sets,
propagates under the joint influence of a boundary attraction
force and a boundary competition force. Unlike other contour
models, the proposed vector field dynamically adapts by updating itself
when a contour reaches a boundary. The model is then more
invariant to initialization and possesses better convergence abilities.
Analytical and comparative results are presented on synthetic and real
images.


Second talk:
Title:
Quality Inspection of Ceramic Tiles: Color Histograms and
Texture Exemplars

Abstract:
In industrial quality inspection of color texture surfaces, such
as ceramic tiles or fabrics, it is important to maintain a
consistent color shade or tonality during production. We present
a multidimensional histogram method with a PCA based noise-removal
scheme to inspect the surfaces.

We also present a new approach to detecting defects in random
textures which requires only very few defect free samples for
unsupervised training. Each product image is divided into overlapping
patches of various sizes. Then, density mixture models are applied
to reduce groupings of patches to a number of textural exemplars,
referred to here as texems, characterizing the means and covariances
of whole sets of image patches. The texems can be viewed as implicit
representations of textural primitives. A multiscale approach is used
to save computational costs. Finally, we perform novelty detection by
applying the lower bound of normal samples likelihoods on the
multiscale defect map of an image to localize defects.


to know more about Dr. Majid Mirmehdi you can visit:
http://www.cs.bris.ac.uk/~majid/