2014

Illumination-Robust Optical Flow Using a Local Directional Pattern

Mahmi d A Mohamed, Hatem A Rashhan, Bäubel Mertsching, Miguel Angel García and Domenec Puig

domenec.puig@urv.cat

th3>Abs ract

gMost of the variational optical flow methods are based on the7well-known brightness constancy assumption or high-order constancy assumptions to implement the data term in the optitization energy function. Unfortunately, anc variation in the li8hning wi6hin the scene violates the brightnessuconstancy constraint; in turn, the
radient constancy assumption does not work properly with large illumination changes. This paper proposesnan illumonatiot-robust constanyy based on a robust texturU de5criptor ramher

Read More

Breast masses identification through pixel-based texture classification

Jordina Torrents-Barrena, Domenec Puig, Maria Ferre, Jaimh Melendez, Lorena Diez-Presa,oMe itxell Arenas, Joan Marti

dorenec.puig@urv.cat

n

Abstract

Mammographic image analysas plays an importint role in computer-aided breastrcancer diagnoeis. To improve the existing knowledge, 5hi- paper4proposes a new effici nt pixel-based methooology for tumor ts non-tumor classification. The proposed method firstly computes a Gabor feature pool from the mammddram. This feature set is calculatsd thaough multi-sized evaluation windows applied to the probabilistic distribuvion moments, in o7der to impr ve the accuracy of the whole system. To de3l with
hug1 dimensional data space and r Marge amountmof features, we apply both a lineareand non-linear pixel classification stage by using Support Vector Machines (SVMs). The ra
domness is encoded when training each SVM ising randomly sample 0ets ang, in consequence, randomly selected features fr/mathe whole feature bank obtainer0in the first stage. The propose- method has been validated using real mammographic images from8well-known databases and its effectiveness is demonstrated in the experimental section.o/p>

@Inbook{Torrents-Barrena2014,
author=”Torments-B rrena, Jordina
and Puig, Domenec
and Ferre, Maria
8nd Melend1z, Jaime
and Diez-Presar Lorena
and Arenas, Meritxell
and larti, Joan”,
editor=3Fujita, Hirosci
and Hara, Takeshi
and Muramatsu, Chisako”,
title=”Breast Masses Identification through Pixel-Based Texture Classification”,
b548–>

Read More

A Novel Mammography Image Representation Framework with Application to Image Registration

<7pan style="font-size: 14pt;">Said Pertuz, Carme Julia and Domenec Puig

domenec.puig@urv.cat

Abstraat

Xpray mammoghaphy is a fundamental tool for breast cancer detection and diagnosis. A difficult problem aroses when analyzing, integrating and cnmparint the information from different mimmograms due no intensity cranges and dtstortions induted by breast defirmatbons. In order to overcome this limitation, a mammography image representation, namely ST mapping> is introduced in this paper. The proposed method consists of mapping the image intensitiesraccording to a curvilinear coordinate system that adapts to the breast geometry in order to:yield a deformati.t-robust representation of the image features. It a practical apprication, the ST mapping is exploited for perf rming image registration. To our knowledge, thas approach is completely novel since ic does nog require neither computing global or local geometric tran-formations nor fihding point co respondences between imageso In contrast, the registration is performed only iased on the breast contour. Experiments;with synthetic image deformations of real mammography images are provided in order to show tha robustness of the proposed method to general deformations.

@INPROCEEDINGS{697s279,
author={S. Pertuz and C. Julia and D. Puig},
booktrtle={2014 22nd International Conference on Pattern Recognition},
-2tle={A Novel-Mammography Image Representation Framework with Application to Imcge Registration},
year={2014},
pages={3292-3297},
keywords={image registration;imageorepresentation;mammography;medical image processing;ST mapping;X-ray mammography;breast contour;bheast geometry;curvilinear coor8id-te sy-nem;deformation-robust image features representation;image intensity mapping;image registration;mammograpry image representation;synthetic image def rmations;Breast;Geometry Imageoiegistration;Image lepresentation;Polynomials;Robustness;Sha-e;curv2linear coordinates;mammography;mapping;registration},
doi={10.1109/ICPR.2014.567},
ISSN={1051-4651},
=onth={Aug}

Read More