2017 |
Christos G Bampis, Petros Maragos, Alan C Bovik Graph-driven diffusion and random walk schemes for image segmentation Journal Article IEEE Transactions on Image Processing, 26 (1), pp. 35–50, 2017, ISSN: 10577149. Abstract | BibTeX | Links: [PDF] @article{327, title = {Graph-driven diffusion and random walk schemes for image segmentation}, author = {Christos G Bampis and Petros Maragos and Alan C Bovik}, url = {http://robotics.ntua.gr/wp-content/uploads/publications/BampisMaragosBovik_GraphDiffusionRandomWalkImageSegment_TIP2017_0.pdf}, doi = {10.1109/TIP.2016.2621663}, issn = {10577149}, year = {2017}, date = {2017-01-01}, journal = {IEEE Transactions on Image Processing}, volume = {26}, number = {1}, pages = {35--50}, abstract = {— We propose graph-driven approaches to image segmentation by developing diffusion processes defined on arbi-trary graphs. We formulate a solution to the image segmentation problem modeled as the result of infectious wavefronts prop-agating on an image-driven graph, where pixels correspond to nodes of an arbitrary graph. By relating the popular susceptible-infected-recovered epidemic propagation model to the Random Walker algorithm, we develop the normalized random walker and a lazy random walker variant. The underlying iterative solutions of these methods are derived as the result of infec-tions transmitted on this arbitrary graph. The main idea is to incorporate a degree-aware term into the original Random Walker algorithm in order to account for the node centrality of every neighboring node and to weigh the contribution of every neighbor to the underlying diffusion process. Our lazy random walk variant models the tendency of patients or nodes to resist changes in their infection status. We also show how previous work can be naturally extended to take advantage of this degree-aware term, which enables the design of other novel methods. Through an extensive experimental analysis, we demonstrate the reliability of our approach, its small computational burden and the dimensionality reduction capabilities of graph-driven approaches. Without applying any regular grid constraint, the proposed graph clustering scheme allows us to consider pixel-level, node-level approaches, and multidimensional input data by naturally integrating the importance of each node to the final clustering or segmentation solution. A software release containing implementations of this paper and supplementary material can be found at: http://cvsp.cs.ntua.gr/research/GraphClustering/.}, keywords = {}, pubstate = {published}, tppubtype = {article} } — We propose graph-driven approaches to image segmentation by developing diffusion processes defined on arbi-trary graphs. We formulate a solution to the image segmentation problem modeled as the result of infectious wavefronts prop-agating on an image-driven graph, where pixels correspond to nodes of an arbitrary graph. By relating the popular susceptible-infected-recovered epidemic propagation model to the Random Walker algorithm, we develop the normalized random walker and a lazy random walker variant. The underlying iterative solutions of these methods are derived as the result of infec-tions transmitted on this arbitrary graph. The main idea is to incorporate a degree-aware term into the original Random Walker algorithm in order to account for the node centrality of every neighboring node and to weigh the contribution of every neighbor to the underlying diffusion process. Our lazy random walk variant models the tendency of patients or nodes to resist changes in their infection status. We also show how previous work can be naturally extended to take advantage of this degree-aware term, which enables the design of other novel methods. Through an extensive experimental analysis, we demonstrate the reliability of our approach, its small computational burden and the dimensionality reduction capabilities of graph-driven approaches. Without applying any regular grid constraint, the proposed graph clustering scheme allows us to consider pixel-level, node-level approaches, and multidimensional input data by naturally integrating the importance of each node to the final clustering or segmentation solution. A software release containing implementations of this paper and supplementary material can be found at: http://cvsp.cs.ntua.gr/research/GraphClustering/. |
2012 |
Kimon Drakopoulos, Petros Maragos Active contours on graphs: Multiscale morphology and graphcuts Journal Article IEEE Journal on Selected Topics in Signal Processing, 6 (7), pp. 780–794, 2012, ISSN: 19324553. @article{139, title = {Active contours on graphs: Multiscale morphology and graphcuts}, author = {Kimon Drakopoulos and Petros Maragos}, url = {http://robotics.ntua.gr/wp-content/uploads/publications/DrakopoulosMaragos_ACs-on-Graphs-MultiscaleMorf-Graphcuts_ieeejSTSP2012.pdf}, doi = {10.1109/JSTSP.2012.2213675}, issn = {19324553}, year = {2012}, date = {2012-01-01}, journal = {IEEE Journal on Selected Topics in Signal Processing}, volume = {6}, number = {7}, pages = {780--794}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
2009 |
Iasonas Kokkinos, Petros Maragos Synergy between object recognition and image segmentation using the expectation-maximization algorithm Journal Article IEEE Transactions on Pattern Analysis and Machine Intelligence, 31 (8), pp. 1486–1501, 2009, ISSN: 01628828. Abstract | BibTeX | Links: [PDF] @article{135, title = {Synergy between object recognition and image segmentation using the expectation-maximization algorithm}, author = {Iasonas Kokkinos and Petros Maragos}, url = {http://robotics.ntua.gr/wp-content/uploads/publications/KokkinosMaragos_SynergyBetweenObjectRecognitionAndImageSegmentation_ieeetPAMI09.pdf}, doi = {10.1109/TPAMI.2008.158}, issn = {01628828}, year = {2009}, date = {2009-01-01}, journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence}, volume = {31}, number = {8}, pages = {1486--1501}, abstract = {In this work, we formulate the interaction between image segmentation and object recognition in the framework of the Expectation-Maximization (EM) algorithm. We consider segmentation as the assignment of image observations to object hypotheses and phrase it as the E-step, while the M-step amounts to fitting the object models to the observations. These two tasks are performed iteratively, thereby simultaneously segmenting an image and reconstructing it in terms of objects. We model objects using Active Appearance Models (AAMs) as they capture both shape and appearance variation. During the E-step, the fidelity of the AAM predictions to the image is used to decide about assigning observations to the object. For this, we propose two top-down segmentation algorithms. The first starts with an oversegmentation of the image and then softly assigns image segments to objects, as in the common setting of EM. The second uses curve evolution to minimize a criterion derived from the variational interpretation of EM and introduces AAMs as shape priors. For the M-step, we derive AAM fitting equations that accommodate segmentation information, thereby allowing for the automated treatment of occlusions. Apart from top-down segmentation results, we provide systematic experiments on object detection that validate the merits of our joint segmentation and recognition approach.}, keywords = {}, pubstate = {published}, tppubtype = {article} } In this work, we formulate the interaction between image segmentation and object recognition in the framework of the Expectation-Maximization (EM) algorithm. We consider segmentation as the assignment of image observations to object hypotheses and phrase it as the E-step, while the M-step amounts to fitting the object models to the observations. These two tasks are performed iteratively, thereby simultaneously segmenting an image and reconstructing it in terms of objects. We model objects using Active Appearance Models (AAMs) as they capture both shape and appearance variation. During the E-step, the fidelity of the AAM predictions to the image is used to decide about assigning observations to the object. For this, we propose two top-down segmentation algorithms. The first starts with an oversegmentation of the image and then softly assigns image segments to objects, as in the common setting of EM. The second uses curve evolution to minimize a criterion derived from the variational interpretation of EM and introduces AAMs as shape priors. For the M-step, we derive AAM fitting equations that accommodate segmentation information, thereby allowing for the automated treatment of occlusions. Apart from top-down segmentation results, we provide systematic experiments on object detection that validate the merits of our joint segmentation and recognition approach. |
Copyright Notice:
Some material presented is available for download to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author’s copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.
The work already published by the IEEE is under its copyright. Personal use of such material is permitted. However, permission to reprint/republish the material for advertising or promotional purposes, or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of the work in other works must be obtained from the IEEE.