Semantic descriptions or attribute representations have been used successfully for object and scene recognition, and for word-spotting. However, these representations have not been explored deeply on human activity re...
详细信息
ISBN:
(纸本)9781450364874
Semantic descriptions or attribute representations have been used successfully for object and scene recognition, and for word-spotting. However, these representations have not been explored deeply on human activity recognition (HAR). Particularly, in the manual order picking process, attribute representations are beneficial for dealing withthe versatility of activities in the process. this paper compares the performance of deep architectures trained using different attribute representations for HAR. Besides, it evaluates their quality from the perspective of practical application.
the proceedings contain 127 papers. the special focus in this conference is on Visual recognition, Detection, Contours, Lines and Paths. the topics include: Finding clusters and components by unsupervised learning;a d...
ISBN:
(纸本)9783540225706
the proceedings contain 127 papers. the special focus in this conference is on Visual recognition, Detection, Contours, Lines and Paths. the topics include: Finding clusters and components by unsupervised learning;a demonstration on text data;the use of graph techniques for identifying objects and scenes in indoor building environments for mobile robots;graphical-based learning environments for patternrecognition;spectral analysis of complex laplacian matrices;a significant improvement of softassign with diffusion kernels;eigenspace method by autoassociative networks for object recognition;extraction of skeletal shape features using a visual attention operator;computing the cyclic edit distance for pattern classification by ranking edit paths;steady state random walks for path estimation;new variational framework for rigid-body alignment;an error-tolerant approximate matching algorithm for attributed planar graphs and its application to fingerprint classification;comparison of algorithms for web document clustering using graphrepresentations of data;a syntactic patternrecognition approach to computer assisted translation;a general methodology for finite-state translation using alignments;a comparison of unsupervised shot classification algorithms for news video segmentation;diagnosis of lung nodule using the semivariogram function;distances between distributions;multiscale curvature assessment of postural deviations;learning people movement model from multiple cameras for behaviour recognition;a comparison of least squares and spectral methods for attributed graph matching and an auction algorithm for graph-based contextual correspondence matching.
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
the field of statistical patternrecognition is characterized by the use of feature vectors for pattern representation, while strings or, more generally, graphs are prevailing in structural patternrecognition. In thi...
详细信息
ISBN:
(纸本)9783540729020
the field of statistical patternrecognition is characterized by the use of feature vectors for pattern representation, while strings or, more generally, graphs are prevailing in structural patternrecognition. In this paper we aim at bridging the gap between the domain of feature based and graphbased object representation. We propose a general approach for transforming graphs into n-dimensional real vector spaces by means of prototype selection and graph edit distance computation. this method establishes the access to the wide range of procedures based on feature vectors without loosing the representational power of graphs. through various experimental results we show that the proposed method, using graph embedding and classification in a vector space, outperforms the tradional approach based on k-nearest neighbor classification in the graph domain.
this book constitutes the refereed proceedings of the 5th INNS IAPR TC3 GIRPR internationalworkshop on Artificial Neural Networks in patternrecognition, ANNPR 2012, held in Trento, Italy, in September 2012. the 21 r...
ISBN:
(数字)9783642332128
ISBN:
(纸本)9783642332111
this book constitutes the refereed proceedings of the 5th INNS IAPR TC3 GIRPR internationalworkshop on Artificial Neural Networks in patternrecognition, ANNPR 2012, held in Trento, Italy, in September 2012. the 21 revised full papers presented were carefully reviewed and selected for inclusion in this volume. they cover a large range of topics in the field of neural network- and machine learning-basedpatternrecognition presenting and discussing the latest research, results, and ideas in these areas.
Matrix representations for graphs play an important role in combinatorics. In this paper, we investigate four matrix representations for graphs and carry out an characteristic polynomial analysis upon them. the first ...
详细信息
ISBN:
(纸本)9783642021237
Matrix representations for graphs play an important role in combinatorics. In this paper, we investigate four matrix representations for graphs and carry out an characteristic polynomial analysis upon them. the first two graph matrices are the adjacency matrix and Laplacian matrix. these two matrices call be obtained straightforwardly from graphs. the second two matrix representations, which are newly introduced [9][3], arc closely related withthe Ihara zeta function and the discrete time quantum walk. they have a similar form and are established from a transformed graph. i.e. the oriented line graph of the original graph. We make use of the characteristic polynomial coefficients of the four matrices to characterize graphs and construct pattern spaces with a fixed dimensionality. Experimental results indicate that the two matrices in the transformed domain perform better than the two matrices in the original graph domain whereas the matrix associated withthe Ihara zeta function is more efficient and effective than the matrix associated withthe discrete time quantum walk and the remaining methods.
Structural patternrecognition describes and classifies data based on the relationships of features and parts. Topological invariants, like the Euler number, characterize the structure of objects of any dimension. Coh...
详细信息
ISBN:
(纸本)9783642021237
Structural patternrecognition describes and classifies data based on the relationships of features and parts. Topological invariants, like the Euler number, characterize the structure of objects of any dimension. Cohomology can provide more refined algebraic invariants to a topological space that does homology. It assigns 'quantities' to the chains used in homology to characterize holes of any dimension. graph pyramids can be used to describe subdivisions of the same object at multiple levels of detail. this paper presents cohomology in the context of structural patternrecognition and introduces an algorithm to efficiency compute representative cocycles (the basic elements of cohomology) in 2D using a graph pyramid. Extension to nD and application in the context of patternrecognition are discussed.
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
暂无评论