Book Section records
https://feeds.library.caltech.edu/people/Weber-M/book_section.rss
A Caltech Library Repository Feedhttp://www.rssboard.org/rss-specificationpython-feedgenenTue, 16 Apr 2024 14:29:46 +0000A probabilistic approach to object recognition using local photometry and global geometry
https://resolver.caltech.edu/CaltechAUTHORS:20190328-144424617
Authors: {'items': [{'id': 'Burl-M-C', 'name': {'family': 'Burl', 'given': 'Michael C.'}}, {'id': 'Weber-M', 'name': {'family': 'Weber', 'given': 'Markus'}}, {'id': 'Perona-P', 'name': {'family': 'Perona', 'given': 'Pietro'}, 'orcid': '0000-0002-7583-5809'}]}
Year: 1998
DOI: 10.1007/bfb0054769
Many object classes, including human faces, can be modeled as a set of characteristic parts arranged in a variable spatial configuration. We introduce a simplified model of a deformable object class and derive the optimal detector for this model. However, the optimal detector is not realizable except under special circumstances (independent part positions). A cousin of the optimal detector is developed which uses "soft" part detectors with a probabilistic description of the spatial arrangement of the parts. Spatial arrangements are modeled probabilistically using shape statistics to achieve invariance to translation, rotation, and scaling. Improved recognition performance over methods based on "hard" part detectors is demonstrated for the problem of face detection in cluttered scenes.https://authors.library.caltech.edu/records/pxy9w-8bg90What do planar shadows tell about scene geometry?
https://resolver.caltech.edu/CaltechAUTHORS:20111201-141431171
Authors: {'items': [{'id': 'Bouguet-J-Y', 'name': {'family': 'Bouguet', 'given': 'Jean-Yves'}}, {'id': 'Weber-M', 'name': {'family': 'Weber', 'given': 'Markus'}}, {'id': 'Perona-P', 'name': {'family': 'Perona', 'given': 'Pietro'}, 'orcid': '0000-0002-7583-5809'}]}
Year: 1999
DOI: 10.1109/CVPR.1999.786986
A method for reconstructing 3D scene geometry from a set of projected shadows is presented. It is composed of two stages. First, the scene geometry is retrieved up to three scalar unknowns using only the information contained in the observed shadow edges on the image plane. Then, the three remaining unknowns are computed making use of the known depths at three points. This technique improves upon previous results in that it does not require the presence of a reference plane in the background. A mathematical analysis is presented using dual-space geometry, a formalism that provides adequate tools to carry out all the derivations in a compact and intuitive manner. A linear algorithm based on singular value decomposition (SVD) is presented leading to a closed form solution for reconstruction.https://authors.library.caltech.edu/records/zne9d-54k64Unsupervised Learning of Models for Recognition
https://resolver.caltech.edu/CaltechAUTHORS:20190829-131534540
Authors: {'items': [{'id': 'Weber-M', 'name': {'family': 'Weber', 'given': 'M.'}}, {'id': 'Welling-M', 'name': {'family': 'Welling', 'given': 'M.'}}, {'id': 'Perona-P', 'name': {'family': 'Perona', 'given': 'P.'}, 'orcid': '0000-0002-7583-5809'}]}
Year: 2000
DOI: 10.1007/3-540-45054-8_2
We present a method to learn object class models from unlabeled and unsegmented cluttered scenes for the purpose of visual object recognition. We focus on a particular type of model where objects are represented as flexible constellations of rigid parts (features). The variability within a class is represented by a joint probability density function (pdf) on the shape of the constellation and the output of part detectors. In a first stage, the method automatically identifies distinctive parts in the training set by applying a clustering algorithm to patterns selected by an interest operator. It then learns the statistical shape model using expectation maximization. The method achieves very good classification results on human faces and rear views of cars.https://authors.library.caltech.edu/records/vwvy7-qbc92Viewpoint-invariant learning and detection of human heads
https://resolver.caltech.edu/CaltechAUTHORS:20111130-141116001
Authors: {'items': [{'id': 'Weber-M', 'name': {'family': 'Weber', 'given': 'M.'}}, {'id': 'EinhÃ¤user-W', 'name': {'family': 'EinhÃ¤user', 'given': 'W.'}}, {'id': 'Welling-M', 'name': {'family': 'Welling', 'given': 'M.'}}, {'id': 'Perona-P', 'name': {'family': 'Perona', 'given': 'P.'}, 'orcid': '0000-0002-7583-5809'}]}
Year: 2000
DOI: 10.1109/AFGR.2000.840607
We present a method to learn models of human heads for the purpose of detection from different viewing angles. We focus on a model where objects are represented as constellations of rigid features (parts). Variability is represented by a joint probability density function (PDF) on the shape of the constellation. In the first stage, the method automatically identifies distinctive features in the training set using an interest operator followed by vector quantization. The set of model parameters, including the shape PDF, is then learned using expectation maximization. Experiments show good generalization performance to novel viewpoints and unseen faces. Performance is above 90% correct with less than 1 s computation time per image.https://authors.library.caltech.edu/records/5dxf6-qh442Towards Automatic Discovery of Object Categories
https://resolver.caltech.edu/CaltechAUTHORS:20111209-113314016
Authors: {'items': [{'id': 'Weber-M', 'name': {'family': 'Weber', 'given': 'M.'}}, {'id': 'Welling-M', 'name': {'family': 'Welling', 'given': 'M.'}}, {'id': 'Perona-P', 'name': {'family': 'Perona', 'given': 'P.'}, 'orcid': '0000-0002-7583-5809'}]}
Year: 2000
DOI: 10.1109/CVPR.2000.854754
We propose a method to learn heterogeneous models of
object classes for visual recognition. The training images
contain a preponderance of clutter and learning is unsupervised.
Our models represent objects as probabilistic constellations
of rigid parts (features). The variability within
a class is represented by a joint probability density function
on the shape of the constellation and the appearance
of the parts. Our method automatically identifies distinctive
features in the training set. The set of model parameters
is then learned using expectation maximization (see the
companion paper [11] for details). When trained on different,
unlabeled and unsegmented views of a class of objects,
each component of the mixture model can adapt to represent
a subset of the views. Similarly, different component
models can also "specialize" on sub-classes of an object
class. Experiments on images of human heads, leaves from
different species of trees, and motor-cars demonstrate that
the method works well over a wide variety of objects.https://authors.library.caltech.edu/records/mn8vs-9b472