A Graph Theoretic Approach for Object Shape Representation in Compositional Hierarchies Using a Hybrid Generative-Descriptive Model

  title={A Graph Theoretic Approach for Object Shape Representation in Compositional Hierarchies Using a Hybrid Generative-Descriptive Model},
  author={{\"U}mit Rusen Aktas and Mete Ozay and Ale{\vs} Leonardis and Jeremy L. Wyatt},
  booktitle={European Conference on Computer Vision},
A graph theoretic approach is proposed for object shape representation in a hierarchical compositional architecture called Compositional Hierarchy of Parts (CHOP). In the proposed approach, vocabulary learning is performed using a hybrid generative-descriptive model. First, statistical relationships between parts are learned using a Minimum Conditional Entropy Clustering algorithm. Then, selection of descriptive parts is defined as a frequent subgraph discovery problem, and solved using a… 

Compositional Hierarchical Representation of Shape Manifolds for Classification of Non-manifold Shapes

A framework to implement the indexing mechanisms for the employment of the vocabulary for structural shape classification is introduced and a disjoint union topology using an indexing mechanism for the formation of shape models on SMs in the vocabulary, recursively is designed.

3D compositional hierarchies for object categorization

This thesis proposes two novel frameworks for learning a multi-layer representation of surface shape features, namely the view-based and the surface-based compositional hierarchical frameworks.

Shapes Similarity and Feature Reconstruction Comparison Based Active Contour Model

A novel active contour based on shape similarity and feature reconstruction comparison is proposed to segmenting ultrasonic image sequence, which can be interpreted as an unsupervised approach of shape prior modeling without a large number of annotated data.



Learning Hierarchical Shape Models from Examples

An algorithm for automatically constructing a decompositional shape model from examples is presented, in which a shape feature at a coarser scale can be decomposed into a collection of attached shape features at a finer scale.

Learning the Compositional Nature of Visual Object Categories for Recognition

  • B. OmmerJ. Buhmann
  • Computer Science
    IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2010
A robust descriptor for local image parts is proposed and it is shown how characteristic compositions of parts can be learned that are based on an unspecific part vocabulary shared between all categories.

Recursive Compositional Models for Vision: Description and Review of Recent Work

It is shown that RCMs generally give state of the art results when applied to a range of different vision tasks and evaluated on the leading benchmarked datasets.

Learning a Hierarchical Deformable Template for Rapid Deformable Object Parsing

It is shown that HDTs achieve state-of-the-art performance for these different tasks when evaluated on data sets with groundtruth (and when compared to alternative algorithms, which are typically specialized to each task).

Indexing hierarchical structures using graph spectra

A framework for indexing such representations that embeds the topological structure of a directed acyclic graph (DAG) into a low-dimensional vector space and establishes the insensitivity of the signature to minor perturbation of graph structure due to noise, occlusion, or node split/merge.

Inference and Learning with Hierarchical Shape Models

This work automates the decomposition of an object category into parts and contours, and discriminatively learn the cost function that drives the matching of the object to the image using Multiple Instance Learning.

Towards Scalable Representations of Object Categories: Learning a Hierarchy of Parts

  • S. FidlerA. Leonardis
  • Computer Science
    2007 IEEE Conference on Computer Vision and Pattern Recognition
  • 2007
This paper proposes a novel approach to constructing a hierarchical representation of visual input that aims to enable recognition and detection of a large number of object categories by learning a hierarchy of spatially flexible compositions in an unsupervised, statistics-driven manner.

Object Categorization: Learning Hierarchical Compositional Representations of Object Structure

This paper will focus on what it believes are two central representational design principles, namely a hierarchical organization of categorical representations, more specifically, the principle of hierarchical compositionality, and statistical, bottom-up learning.

Hierarchical Matching of Deformable Shapes

A new hierarchical representation for two-dimensional objects that captures shape information at multiple levels of resolution is described, based on a hierarchical description of an object's boundary, which leads to richer geometric models and more accurate recognition results.

A minimum description length approach to statistical shape modeling

Results are given for several different training sets of two-dimensional boundaries, showing that the proposed method constructs better models than other approaches including manual landmarking-the current gold standard and can be extended straightforwardly to three dimensions.