Irregular pyramids are made of a stack of successively reduced graphs embedded in the plane. Such pyramids are often used within the segmentation and the connected component analysis frameworks to detect meaningful ob...
详细信息
ISBN:
(纸本)3540252703
Irregular pyramids are made of a stack of successively reduced graphs embedded in the plane. Such pyramids are often used within the segmentation and the connected component analysis frameworks to detect meaningful objects together withtheir spatial and topological relationships. the graphs reduced in the pyramid may be region adjacency graphs, dual graphs or combinatorial maps. Using any of these graphs each vertex of a reduced graph encodes a region of the image. Using simple graphs one edge between two vertices encodes the existence of a common boundary between two regions. Using dual graphs and combinatorial maps, each connected boundary segment between two regions is associated to one edge. Moreover, special edges called loops may be used to differentiate a special type of adjacency where one region surrounds the other. We show in this article that the loop information does not allow to distinguish inside and outside of the loop by local computations. We provide a method based on the combinatorial pyramid framework which uses the orientation explicitly encoded by combinatorial maps to determine inside and outside with local calculus.
A concept relating story-board description of video sequences with spatio-temporal hierarchies build by local contraction processes of spatio-temporal relations is presented. Object trajectories are curves in which th...
详细信息
In this paper, an experimental comparison among three structural approaches to fingerprint classification is reported. Main pros and cons of such approaches are investigated by experiments and discussed. Moreover, the...
详细信息
In this paper we explore how a spectral technique suggested by quantum walks can be used to distinguish non-isomorphic cospectral graphs. Reviewing ideas from the field of quantum computing we recall the definition of...
详细信息
this paper shows how strings can be used in a natural images classification task. We propose to build an attributed string from a set of regions of interest detected thanks to an interest point detector. these salient...
详细信息
We present a novel approach to the matching of subgraphs for object recognition in computer vision. Feature similarities between object model and scene graph are complemented with a regularization term that measures d...
详细信息
ISBN:
(纸本)3540302875
We present a novel approach to the matching of subgraphs for object recognition in computer vision. Feature similarities between object model and scene graph are complemented with a regularization term that measures differences of the relational structure. For the resulting quadratic integer program, a mathematically tight relaxation is derived by exploiting the degrees of freedom of the embedding space of positive semidefinite matrices. We show that the global minimum of the relaxed convex problem can be interpreted as probability distribution over the original space of matching matrices, providing a basis for efficiently sampling all close-to-optimal combinatorial matchings within the original solution space. As a result, the approach can even handle completely ambiguous situations, despite uniqueness of the relaxed convex problem. Exhaustive numerical experiments demonstrate the promising performance of the approach which - up to a single inevitable regularization parameter that weights feature similarity against structural similarity - is free of any further tuning parameters.
the proceedings contain 26 papers. the topics discussed include: picture ID authentication using invisible watermark and facial recognition features;a new REF classifier for buried tag recognition;novel circular-shift...
ISBN:
(纸本)9728865287
the proceedings contain 26 papers. the topics discussed include: picture ID authentication using invisible watermark and facial recognition features;a new REF classifier for buried tag recognition;novel circular-shift invariant clustering;inductive string template-based learning of spoken language;a multi-resolution learning approach to tracking concept drift and recurrent concepts;automatic recognition of pollutants in packaged foods from x-ray imaging;car license plate extraction from video stream in complex environment;dynamic feature selection and coarse-to-fine search for content-based image retrieval;automated annotation of multimedia audio data with affective labels for information management;fast algorithm for optimal polygonal approximation of shape boundaries;activity identification and visualization;evaluating patternrecognition techniques in intrusion detection systems;and a comparison of methods for web document classification.
Reverse-convex programming (RCP) concerns global optimization of a specific class of non-convex optimization problems. We show that a recently proposed model for sparse non-negative matrix factorization (NMF) belongs ...
详细信息
ISBN:
(纸本)3540302875
Reverse-convex programming (RCP) concerns global optimization of a specific class of non-convex optimization problems. We show that a recently proposed model for sparse non-negative matrix factorization (NMF) belongs to this class. based on this result, we design two algorithms for sparse NMF that solve sequences of convex secondorder cone programs (SOCP). We work out some well-defined modifications of NMF that leave the original model invariant from the optimization viewpoint. they considerably generalize the sparse NMF setting to account for uncertainty in sparseness, for supervised learning, and, by dropping the non-negativity constraint, for sparsity-controlled PCA.
the proceedings contain 42 papers. the topics discussed include: adaptive simulated annealing for energy minimization problem in a marked point process application;a computational approach to Fisher information geomet...
详细信息
ISBN:
(纸本)3540302875
the proceedings contain 42 papers. the topics discussed include: adaptive simulated annealing for energy minimization problem in a marked point process application;a computational approach to Fisher information geometry with applications to image analysis;optimizing the Cauchy-Schwarz PDF distance for information theoretic, non-parametric clustering;color correction of underwater images for aquatic robot inspection;handling missing data in the computation of 3D affine transformations;geodesic image matching: a wavelet based energy minimization scheme;segmentation informed by manifold learning;and edge strength functions as shape priors in image segmentation.
暂无评论