logo INRIA
logo Ariana
The team ~ Raffaele Gaetano Tuesday, June 25th 2024, 06:26

Raffaele Gaetano

Document Actions
  • Print this page
Former Postdoc, Universita' degli Studi Federico II di Napoli

motcle Keywords : Markov Random Fields, Multiscale Modeling, Texture, Segmentation, Classification
demos Demo : see this author's demo
plus Contact :

Mail :raffaeledotgaetanoatinriadotfr
Phone :(39)081-768-38-37
Fax :(39)081-768-31-49
Postal adress :Universita' degli Studi "Federico II" di Napoli
Dipartimento di Ingegneria Biomedica, Elettronica e delle Telecomunicazioni
Fabbricato 3/A, Stanza 4.26
via Claudio, 21
80125 Napoli
plus Abstract :

Segmentation is a low-level processing aimed at the partition of an image in disjoint regions, each one homogeneous with respect to some properties like intensity, texture, shape, etc. Such a task is needed in many high-level processing and applications in such diverse fields as remote-sensing, medical imaging, video coding, and industrial automation, just to name a few.

In my research activity, I deal with both the problem of color based image segmentation, that is based on some form of homogeneity in the color/spectral properties of the image, and the more complex task of texture based segmentation, where the aim is to recognize complex structures in the image which are typically non homogeneous in terms of spectral properties.

Concerning color based segmentation, we focus on a specific class of Markov Random Field (MRF) probability models, namely the
Tree-Structured Markov Random Fields (TS-MRF), recently proposed to provide a hierarchical multiscale description of images. Based on such a model, the unsupervised image segmentation is carried out by means of a sequence of nested class splits, where each class is modeled as a local binary MRF.

As a first contribution, the model has been first extended to generic tree structures removing the unnecessary binary constraint, and then a new TS-MRF unsupervised segmentation technique has been devised which improves upon the original algorithm by selecting a better tree structure and eliminating spurious classes. Such results are obtained by using the Mean-Shift procedure to estimate the number of pdf modes at each node, and to obtain a more reliable initial clustering for subsequent MRF optimization. To this end,
a new reliable and fast clustering algorithm based on the Mean-Shift technique has been developed, which makes use of a variable-bandwidth strategy based on the k-Nearest Neighbors (k-NN) technique, and is implemented with a speed-up strategy that cuts significantly the computational complexity. Experimental results on synthetic data and real life images from the remote sensing domain prove the potential of the proposed method.

Turning to texture based segmentation, the activity is focused on a novel multiscale texture model, and a related algorithm for the unsupervised segmentation of color images. Elementary textures are characterized by their spatial interactions with neighboring regions along selected directions. Such interactions are modeled in turn by means of a set of Markov chains, one for each direction, whose parameters are collected in a feature vector that synthetically describes the texture. Based on the feature vectors, the texture are then recursively merged, giving rise to larger and more complex textures, which appear at different scales of observation: accordingly, the model is named Hierarchical Multiple Markov Chain (H-MMC).

The Texture Fragmentation and Reconstruction (TFR) algorithm, addresses the unsupervised segmentation problem based on the H-MMC model. The ``fragmentation'' step allows one to find the elementary textures of the model, while the ``reconstruction'' step defines the hierarchical image segmentation based on a probabilistic measure (texture score)
which takes into account both region scale and inter-region interactions.

The performance of the proposed method was assessed through the Prague segmentation benchmark, based on mosaics of real natural textures, and also tested on real-world natural images from the Berkeley dataset. Finally, an application of the TFR algorithm for the unsupervised segmentation of multiresolution remotely sensed images is proposed, based on the significant presence of textural content in last generation high-resolution satellite images. The obtained results further assess the potential of the proposed method for such real life applications.

plus Short Bio :

Raffaele Gaetano received the laurea (M.S.) degree in computer engineering from the University ``Federico II'' of Naples, Italy,
in December 2004. From November 2005 he is working towards the Ph.D. degree in electronic and telecommunication engineering at the same university.

He is a member of the research group on Image Processing (GRIP) of the Department of Biomedics, Electronics and Telecommunication Engineering,
University of Naples. His main research activity is in the field of statistical image analysis and processing: in particular, his interests
are related to color and texture based hierarchical image segmentation, with main application to the classification of remote sensing images.

He conducts research on part of these topics in collaboration with INRIA, Sophia Antipolis (France), where he spent two different stays between 2006 and 2008 as a visiting student.

plus Last publications in Ariana Research Group :
Morphological road segmentation in urban areas from high resolution satellite images.
R. Gaetano and J. Zerubia and G. Scarpa and G. Poggi. In International Conference on Digital Signal Processing, Corfu, Greece, July 2011.
Keywords : Segmentation, Classification, skeletonization , pattern recognition, shape analysis.
Graph-based Analysis of Textured Images for Hierarchical Segmentation.
R. Gaetano and G. Scarpa and T. Sziranyi. In Proc. British Machine Vision Conference (BMVC), Aberystwyth, UK, August 2010.
Hierarchical Multiple Markov Chain Model for Unsupervised Texture Segmentation.
G. Scarpa and R. Gaetano and M. Haindl and J. Zerubia. IEEE Trans. on Image Processing, 18(8): pages 1830-1843, August 2009.
Keywords : Hierarchical Image Models, Markov Process, Pattern Analysis.
publis All publications in Ariana Research Group
Copyright © 2005 - Project Ariana - webmaster
  • WCAG
  • valid XHTML
  • valid CSS