9,490 Hits in 5.1 sec

Geometric determinants of shape segmentation: Tests using segment identification

Elias H. Cohen, Manish Singh
2007 Vision Research  
The geometric determinants of shape decomposition were studied using a performance-based method.  ...  Observers' identification of contour segments was shown to be systematically modulated by their curvature properties, and by the geometric properties of the enclosed region.  ...  This paper reports a series of psychophysical experiments designed to quantify geometric influences on the part-based representation of visual shape.  ... 
doi:10.1016/j.visres.2007.06.021 pmid:17868766 fatcat:5vyn2c525beqbew4zugk5ednfe

A Novel Algorithm for Exact Concave Hull Extraction [article]

Kevin Christopher VanHorn, Murat Can Çobanoğlu
2022 arXiv   pre-print
In this study, we present a novel algorithm that can provide vertex-minimized concave hulls with maximal (i.e. pixel-perfect) resolution and is tunable for speed-efficiency tradeoffs.  ...  Our method provides advantages in multiple downstream applications including data compression, retrieval, visualization, and analysis.  ...  Adaptive Geometric Contouring Representation AGCR is a fully lossless partitioning strategy that facilitates the compression, visualization, and retrieval of images with a high bit-depth, dynamic range  ... 
arXiv:2206.11481v1 fatcat:z5zmgvnubrfrfodmkf437q2wja

Texture Segmentation by Grouping Ellipse Ensembles via Active Contours

Gui-Song Xia, Fei Yuan
2011 Procedings of the British Machine Vision Conference 2011  
We address the problem of unsupervised segmentation of textural images by relying on morphological image representations and active contours.  ...  More precisely, starting with the assumption that textures are statistical ensembles of local image structures, known as textons, we first suggest to represent a texture image through a tree of ellipses  ...  Segmentation by grouping ellipses with active contours Partitioning an image into different regions of homogeneous texture with active contours has been widely studied [2, 14, 20] .  ... 
doi:10.5244/c.25.122 dblp:conf/bmvc/XiaY11 fatcat:2xvobk4bczc6zekqnqhypl6ez4

Symbolic indexing of cardiological sequences through dynamic curve representations [chapter]

M. Baroni, G. Congiu, A. Bimbo, A. Evangelisti, E. Vicario
1995 Lecture Notes in Computer Science  
2D shapes deriving from dynamic cardiac analyses.  ...  These features can be exploited to build up symbolic representations of visual data in medical reports and to index them within large databases.  ...  Visual Data Representation Following the results of studies on human perception, the representation of the shape of a curve can be reduced to the representation of a set of sub-curves, each characterized  ... 
doi:10.1007/3-540-60298-4_323 fatcat:qtp2cimlb5czdikwlegcjzt4cu

CSDM: Fusion of orthographic contour signature and distribution matrix for 3D object global representation and object recognition

Mingliang Fu, Haitao Luo, Weijia Zhou
2017 2017 IEEE International Conference on Robotics and Biomimetics (ROBIO)  
After that, the sub-histogram of contour signature and distribution matrix can be determined from orthographic 2D projected patterns.  ...  The proposed descriptor forms a comprehensive description of an object instance by encoding projection statistics in terms of contour signature and distribution matrix (CSDM).  ...  For a better visualization, contour signatures are a real-value representation with normalization step in Fig. 1(f) and (g) .  ... 
doi:10.1109/robio.2017.8324778 dblp:conf/robio/FuLZ17 fatcat:koezeye5a5fm5c2epvtryceidy

A Review on 2D Image Representation Methods

Bineeth Kuriakose, Preena K P
2015 International Journal of Engineering Research and  
Image Representation is the process of generating descriptions from the visual contents of an image.  ...  The paper ends with the suggestion of introducing a representation which can understandable by both a human and machine.  ...  Structural contour-based approaches include chain code [32] , polygon decomposition [33] , b-splines [34] , and shape invariants such as geometric, algebraic and differential invariants.  ... 
doi:10.17577/ijertv4is041201 fatcat:cbvyupjxmnb7hmv5vsdi23yi5e

Visual judgment of similarity across shape transformations: Evidence for a compositional model of articulated objects

Elan Barenholtz, Michael J. Tarr
2008 Acta Psychologica  
Two types of comparisons were made: in the figure/ground-reversal, the invalid articulation consisted of exactly the same contour transformation as the valid one with reversed figural polarity.  ...  We compared similarity judgments in a task in which subjects had to decide which of the two transformed versions of a 'base' shape-one a 'biologically valid' articulation and one a geometrically similar  ...  Knowledge of these geometric regularities may provide the visual system with a capacity to 'predict' the kinds of shape changes an object may undergo.  ... 
doi:10.1016/j.actpsy.2008.03.007 pmid:18466857 fatcat:cb66qdw5vfh6la754lrifvoyni

A New Distance Measure for Probabilistic Shape Modeling [chapter]

Wei-Jun Chen, Joachim M. Buhmann
2003 Lecture Notes in Computer Science  
to characterize the description quality of arbitrary model/shape pairs.  ...  Experiments show that an optimization procedure, which maximize the model probability, generates robust and visually pleasing geometric models for data.  ...  tractable representations of contours or surfaces.  ... 
doi:10.1007/978-3-540-45243-0_65 fatcat:6aw7a3sp4rhqpexne7ltr5jyhu

Iconic Retrieval by Contents from Databases of Cardiological Sequences [chapter]

Gianfranco Congiu, Alberto Bimbo, Enrico Vicario
1995 Visual Database Systems 3  
Qualitative static and dynamic shape descriptors are introduced to provide a symbolic representation of the evolution of deformable shapes, and a language based on Interval Logic is presented which supports  ...  In this paper, the case of time-varying imaged carves is addressed with reference to a database of cineangiographic reports.  ...  a symbolic characterization of their geometric shape.  ... 
doi:10.1007/978-0-387-34905-3_10 fatcat:axlkwnae3zhhjajdferxietae4

KIPPI: KInetic Polygonal Partitioning of Images

Jean-Philippe Bauchet, Florent Lafarge
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition  
Existing algorithms produce homogeneously-sized polygons that fail to capture thin geometric structures and over-partition large uniform areas.  ...  Recent works showed that floating polygons can be an interesting alternative to traditional superpixels, especially for analyzing scenes with strong geometric signatures, as man-made environments.  ...  Visual comparisons with superpixel and polygonal partitioning methods.  ... 
doi:10.1109/cvpr.2018.00332 dblp:conf/cvpr/BauchetL18 fatcat:ti6pgnssirhxtdpvpjutw5flri

Review of Nuclei Detection, Segmentation in Microscopic Images

Rujuta O, Vyavahare AJ
2017 Journal of Bioengineering and Biomedical Sciences  
Recently some automatic methods have been evolving in digital histopathology with growing application related to nuclear detection and segmentation.  ...  Generally nuclear shape is convex in shape therefore overlapping nuclei detected by concavities has to be separate out through geometric reasoning, which is explained by following steps: 1) Detection of  ...  The obtained result is a binarized image of blobs (a single nucleus or a clump of nuclei), which are either validated or partitioned further through geometric reasoning.  ... 
doi:10.4172/2155-9538.1000227 fatcat:xxvyqhsghzgplddods4bjlulq4

Face Detection And Segmentation On A Hierarchical Image Representation

Veronica Vilaplana, F. Marques
2007 Zenodo  
Figure 4: Region-based hierarchical representation FACE MODEL The face model is a characterization of the face class in terms of a set of visual descriptors.  ...  Original image (a), best representation of the face in the BPT (b), initial partition (c), shape matching with an elliptical shape model (d) and extended node (e).  ... 
doi:10.5281/zenodo.40604 fatcat:uzjbxma6qfhithkd4gh7ohmhfi

User-Adaptive Sketch-Based 3-D CAD Model Retrieval

Yong-Jin Liu, Xi Luo, A. Joneja, Cui-Xia Ma, Xiao-Lan Fu, Dawei Song
2013 IEEE Transactions on Automation Science and Engineering  
Note to Practitioners-Engineering data reuse with the incorporation of modeling knowledge is important in product design.  ...  The authors would also like to thank Princeton Graphics Group for sharing their code implementing suggestive contours and apparent ridges.  ...  Similar to the angular partitioning of abstract images, the shape context descriptor proposed in [4] utilized a histogram in log-polar space that actually leads to a histogram with partitioning along  ... 
doi:10.1109/tase.2012.2228481 fatcat:itpx5ozihjh4niycpbdto2giw4

Part description and segmentation using contour, surface, and volumetric primitives

Alok Gupta, Ruzena K. Bajcsy, Bernd Girod
1990 Sensing and Reconstruction of Three-Dimensional Objects and Scenes  
Unlike previous approaches, we have used geometric properties derived from both boundarybased (surface contours and occluding contours), and primitive-based (quadric patches and superquadric models) representations  ...  Unlike previous approaches, we have used geometric properties derived from both boundary-based (surface contours and occluding contours), and primitive-based (quadric patches and superquadric models) representations  ...  Curve Representation 4 Surface Contours and Patches Introduction For visual discrimination, shape plays a very important role.  ... 
doi:10.1117/12.20020 fatcat:eanenwy3izdwjiij2rfucyaqhe

Characterizing Images by the Gromov-Hausdorff Distances Between Derived Hierarchies

Amin Fehri, Santiago Velasco-Forero, Fernand Meyer
2018 2018 25th IEEE International Conference on Image Processing (ICIP)  
A hierarchy is a series of nested partitions in which a coarser partition results from merging regions of finer ones.  ...  In this paper the hierarchies are constructed with the versatile stochastic watershed algorithm and their inter-distances are measured with the Gromov-Hausdorff distance.  ...  The main idea is to quantify the distance between different hierarchical representations to characterize images.  ... 
doi:10.1109/icip.2018.8451522 dblp:conf/icip/FehriVM18 fatcat:dpjdic36ubahjdkuatl4phsgdu
« Previous Showing results 1 — 15 out of 9,490 results