Slide
Centre Interdisciplinaire
de Recherche et d’Innovation
en Cybersécurité et Société
de Recherche et d’Innovation
en Cybersécurité et Société
1.
Larivière, G.; Allili, M. S.
A learning probabilistic approach for object segmentation Article d'actes
Dans: Proceedings of the 2012 9th Conference on Computer and Robot Vision, CRV 2012, p. 86–93, Toronto, ON, 2012, ISBN: 978-076954683-4 (ISBN), (Journal Abbreviation: Proc. Conf. Comput. Rob. Vis., CRV).
Résumé | Liens | BibTeX | Étiquettes: Algorithms, Computer vision, fragments, Image segmentation, Mean shift algorithm, mean-shift algorithm, Object recognition, Object segmentation, Object shape, Optimal segmentation, Probabilistic approaches, Probabilistic Learning, Segmentation process
@inproceedings{lariviere_learning_2012,
title = {A learning probabilistic approach for object segmentation},
author = {G. Larivière and M. S. Allili},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-84878376248&doi=10.1109%2fCRV.2012.19&partnerID=40&md5=044a531d9d6de8036a434993f7b5d7ba},
doi = {10.1109/CRV.2012.19},
isbn = {978-076954683-4 (ISBN)},
year = {2012},
date = {2012-01-01},
booktitle = {Proceedings of the 2012 9th Conference on Computer and Robot Vision, CRV 2012},
pages = {86–93},
address = {Toronto, ON},
abstract = {This paper proposes a new method for figure-ground image segmentation based on a probabilistic learning approach of the object shape. Historically, segmentation is mostly defined as a data-driven bottom-up process, where pixels are grouped into regions/objects according to objective criteria, such as region homogeneity, etc. In particular, it aims at creating a partition of the image into contiguous, homogenous regions. In the proposed work, we propose to incorporate prior knowledge about the object shape and category to segment the object from the background. The segmentation process is composed of two parts. In the first part, object shape models are built using sets of object fragments. The second part starts by first segmenting an image into homogenous regions using the mean-shift algorithm. Then, several object hypotheses are tested and validated using the different object shape models as supporting information. As an output, our algorithm identifies the object category, position, as well as its optimal segmentation. Experimental results show the capacity of the approach to segment several object categories. © 2012 IEEE.},
note = {Journal Abbreviation: Proc. Conf. Comput. Rob. Vis., CRV},
keywords = {Algorithms, Computer vision, fragments, Image segmentation, Mean shift algorithm, mean-shift algorithm, Object recognition, Object segmentation, Object shape, Optimal segmentation, Probabilistic approaches, Probabilistic Learning, Segmentation process},
pubstate = {published},
tppubtype = {inproceedings}
}
This paper proposes a new method for figure-ground image segmentation based on a probabilistic learning approach of the object shape. Historically, segmentation is mostly defined as a data-driven bottom-up process, where pixels are grouped into regions/objects according to objective criteria, such as region homogeneity, etc. In particular, it aims at creating a partition of the image into contiguous, homogenous regions. In the proposed work, we propose to incorporate prior knowledge about the object shape and category to segment the object from the background. The segmentation process is composed of two parts. In the first part, object shape models are built using sets of object fragments. The second part starts by first segmenting an image into homogenous regions using the mean-shift algorithm. Then, several object hypotheses are tested and validated using the different object shape models as supporting information. As an output, our algorithm identifies the object category, position, as well as its optimal segmentation. Experimental results show the capacity of the approach to segment several object categories. © 2012 IEEE.
2.
Allili, M. S.; Ziou, D.
Object of interest segmentation and tracking by using feature selection and active contours Article d'actes
Dans: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Minneapolis, MN, 2007, ISBN: 1-4244-1180-7 978-1-4244-1180-1, (ISSN: 10636919).
Résumé | Liens | BibTeX | Étiquettes: Feature extraction, Image acquisition, Image segmentation, Object recognition, Object segmentation, Objective functions, Optimization
@inproceedings{allili_object_2007,
title = {Object of interest segmentation and tracking by using feature selection and active contours},
author = {M. S. Allili and D. Ziou},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-34948855864&doi=10.1109%2fCVPR.2007.383449&partnerID=40&md5=2429a266190c72bb8fb8d3776c444906},
doi = {10.1109/CVPR.2007.383449},
isbn = {1-4244-1180-7 978-1-4244-1180-1},
year = {2007},
date = {2007-01-01},
booktitle = {Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition},
address = {Minneapolis, MN},
abstract = {Most image segmentation algorithms in the past are based on optimizing an objective function that aims to achieve the similarity between several low-level features to build a partition of the image into homogeneous regions. In the present paper, we propose to incorporate the relevance (selection) of the grouping features to enforce the segmentation toward the capturing of objects of interest. The relevance of the features is determined through a set of positive and negative examples of a specific object defined a priori by the user. The calculation of the relevance of the features is performed by maximizing an objective function defined on the mixture likelihoods of the positive and negative object examples sets. The incorporation of the features relevance in the object segmentation is formulated through an energy functional which is minimized by using level set active contours. We show the efficiency of the approach on several examples of object of interest segmentation and tracking where the features relevance is used. © 2007 IEEE.},
note = {ISSN: 10636919},
keywords = {Feature extraction, Image acquisition, Image segmentation, Object recognition, Object segmentation, Objective functions, Optimization},
pubstate = {published},
tppubtype = {inproceedings}
}
Most image segmentation algorithms in the past are based on optimizing an objective function that aims to achieve the similarity between several low-level features to build a partition of the image into homogeneous regions. In the present paper, we propose to incorporate the relevance (selection) of the grouping features to enforce the segmentation toward the capturing of objects of interest. The relevance of the features is determined through a set of positive and negative examples of a specific object defined a priori by the user. The calculation of the relevance of the features is performed by maximizing an objective function defined on the mixture likelihoods of the positive and negative object examples sets. The incorporation of the features relevance in the object segmentation is formulated through an energy functional which is minimized by using level set active contours. We show the efficiency of the approach on several examples of object of interest segmentation and tracking where the features relevance is used. © 2007 IEEE.