ARTISAN: a shape retrieval system based on boundary family indexing

@inproceedings{Eakins1996ARTISANAS,
  title={ARTISAN: a shape retrieval system based on boundary family indexing},
  author={John P. Eakins and Kevin Shields and Jago M. Boardman},
  booktitle={Electronic Imaging},
  year={1996}
}
Successful retrieval of images by shape feature is likely to be achieved only if we can mirror human similarity judgments. Following Biederman's theory of recognition-by-components, we postulate that shape analysis for retrieval should characterize an image by identifying properties such as collinearity, shape similarity and proximity in component boundaries. Such properties can then be used to group image components into families, from which indexing features can be derived. We are currently… 
Retrieval of trade mark images by shape feature
TLDR
The aim of the current ARTISAN (Automatic Retrieval of Trademark Images by Shape ANalysis) project is to develop and evaluate a prototype shape retrieval system for trade mark images consisting of abstract geometric designs, and to assess the feasibility of generalizing the image retrieval approach developed in the earlier SAFARI system to a wider range of image types.
Evaluation of a Trademark Image Retrieval System
TLDR
The results suggest strongly that the basic ARTISAN approach is valid, though the present version has significant limitations, particularly when handling badly-scanned images or images with implied shape features.
Appearance-based Global Similarity Retrieval
TLDR
The hypothesis is that, image intensity surface features can be used to compute appearance similarity and the results support the hypothesis in that images similar in appearance are ranked close together.
Multi-Object Shape Retrieval Using Curvature Trees
TLDR
This work presents a geometry-based image retrieval approach for multi-object images by developing an effective shape matching method for closed boundaries and proposes an algorithm, based on Gestalt principles, to detect and extract high-level boundaries (or envelopes), which may evolve as a result of the spatial arrangement of a group of image objects.
Appearance-Based Global Similarity Retrieval of Images
TLDR
The hypothesis is that image intensity surface features can be used to compute appearance similarity, and the results support the hypothesis in that images similar in appearance are ranked close together.
Multi-modal Retrieval of Trademark Images Using Global Similarity TITLE2:
TLDR
A trademark database obtained from the US Patent and Trademark Office containing 63000 design only trademark images and text is used to demonstrate scalability of the image search method and multi-modal retrieval.
Similarity evaluation based on image primitives
TLDR
A new framework for the perceptually relevant comparison of figurative images, especially trademark logos is presented, which allows for a considerable improvement of content based image retrieval in trademark images.
Layout indexing of trademark images
TLDR
This paper proposes a framework in which a graph-based indexing schema will be applied to facilitate efficient trademark retrieval based on spatial relations between image components, regardless of mutual shape similarity.
Trademark image retrieval by local features
TLDR
The author has investigated the use of local image features as a means to finding similarities between trademark images that only partially match in terms of their subcomponents, and the intrinsically non-parametric machine learning algorithm ID3 (Iterative Dichotomiser 3) was selected to construct decision trees by means of dynamic rule induction.
Comparison of the effectiveness of alternative feature sets in shape retrieval of multicomponent images
TLDR
Investigating the relative effectiveness of several types of global shape feature, both singly and in combination, suggests that a wide variety of shape feature combinations can provide adequate discriminating power for effective shape retrieval in multi-component image collections such as trademark registries.
...
...

References

SHOWING 1-10 OF 62 REFERENCES
Similar-Shape Retrieval in Shape Data Management
TLDR
This work discusses the central issues in similar-shape retrieval and explains how these issues are resolved in a shape retrieval scheme called FIBSSR (Feature Index-Based Similar-Shape Retrieval).
Content-based indexing technique using relative geometry features
TLDR
A content-based indexing technique which is based on the theory of weighted center-of-mass, which can be used for retrieving magnetic resonance images of patients'' chests within the medical image domain.
Retrieving images by 2D shape: a comparison of computation methods with human perceptual judgments
TLDR
Shape similarity using algebraic moments, spline curve distances, cumulative turning angle, signal of curvature and Hausdorff- distance were compared to human similarity judgments on twenty test shapes against a large image database.
Hierarchical approach to feature indexing
We extend our previous approach to 2-D shape indexing, data-driven indexed hypotheses, to hierarchical features. It is shown mathematically and experimentally that an index based on hierarchical
Perceptual Organization for Scene Segmentation and Description
TLDR
A data-driven system for segmenting scenes into objects and their components is presented, and applications of collations to stereo correspondence, object-level segmentation, and shape description are illustrated.
Recognition-by-components: a theory of human image understanding.
TLDR
Recognition-by-components (RBC) provides a principled account of the heretofore undecided relation between the classic principles of perceptual organization and pattern recognition.
Efficient content-based retrieval in image databases: a probabilistic approach
TLDR
The paper presents two approaches for improving the efficiency of query processing by (a) reducing the number of accesses to the Image Database and (b) by reducing theNumber of accesse to the signature file.
Hierarchical classification method and its application in shape representation
TLDR
An hierarchical classification technique is developed that enables similarity matching between objects, with the position in the hierarchy signifying the level of generality to be used in the query.
Efficient and Effective Querying by Image Content
TLDR
A new theorem is introduced that makes indexing possible by bounding the non-Euclidean, full cross-term quadratic distance expression with a simple Euclidean distance, and it is illustrated how orthogonal transforms, such as the Karhunen Loeve transform, can help reduce the dimensionality, without introducing false dismissals.
Database architecture for content-based image retrieval
TLDR
This paper adopts both an image model and a user model to interpret and operate the contents of image data from the user''s viewpoint, and develops algorithms developed on the TRADEMARK and the ART MUSEUM.
...
...