WARP: accurate retrieval of shapes using phase of Fourier descriptors and time warping distance

@article{Bartolini2005WARPAR,
  title={WARP: accurate retrieval of shapes using phase of Fourier descriptors and time warping distance},
  author={Ilaria Bartolini and Paolo Ciaccia and Marco Patella},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year={2005},
  volume={27},
  pages={142-147}
}
Effective and efficient retrieval of similar shapes from large image databases is still a challenging problem in spite of the high relevance that shape information can have in describing image contents. We propose a novel Fourier-based approach, called WARP, for matching and retrieving similar shapes. The unique characteristics of WARP are the exploitation of the phase of Fourier coefficients and the use of the dynamic time warping (DTW) distance to compare shape descriptors. While phase… 

Figures and Tables from this paper

Correlating fourier descriptors of local patches for road sign recognition

TLDR
The authors show that the sum-of-squared differences of FDs can be computed without explicitly de-rotating the contours, and demonstrate that correlation-based approach outperforms AFDs and WARP on real data.

Shape Retrieval Using Normalized Fourier Descriptors Based Signatures and Cyclic Dynamic Time Warping

TLDR
A different signature method to provide true rotation invariance and a Cyclic Dynamic Time Warping dissimilarity measure to achieve true starting-point invariance in shape comparisons are proposed.

Phase preserving Fourier descriptor for shape-based image retrieval

Shape retrieval using triangle-area representation and dynamic space warping

Patch Contour Matching by Correlating Fourier Descriptors

TLDR
It is shown that the sum-of-squared differences of FDs can be computed without explicitly de-rotating the contours, and it is demonstrated that the correlation based approach outperforms AFDs on real world data.

Supporting exact indexing of arbitrarily rotated shapes and periodic time series under Euclidean and warping distance measures

TLDR
The indexing technique can be used to index star light curves, an important type of astronomical data, without modification and with all the most popular distance measures including Euclidean distance, dynamic time warping and Longest Common Subsequence.

Shape Retrieval Using Shape Contexts and Cyclic Dynamic Time Warping

TLDR
A better selection of landmark points based on a low-pass filtering of the shape contour and consider that shape context at landmarks along the contour form a cyclic sequence, which can be properly compared by means of Cyclic Dynamic Time Warping.

Shape Based Image Retrieval Using Fused Features

TLDR
The Fourier Descriptors, Moment-Based Features, Hierarchical Centroids and Histogram of Oriented Gradients have been applied for extraction of images from datasets and it has been evident that by fusion of features they obtained approximately 90% accurate and better results.
...

References

SHOWING 1-10 OF 27 REFERENCES

Using the Time Warping Distance for Fourier-Based Shape Retrieval

TLDR
This paper proposes a new approach (based on the Discrete Fourier Transform) for assessing the shape similarity between two objects, allowing a (limited) elastic stretching of the time axis to accommodate possible phase differences.

A Comparative Study of Fourier Descriptors for Shape Representation and Retrieval

TLDR
Different FDs are studied and a Java retrieval framework is built to compare shape retrieval performance using different FDs in terms of computation complexity, robustness, convergence speed and retrieval performance.

Efficient retrieval of similar time sequences under time warping

TLDR
This work proposes a modification of the so called "FastMap", to map sequences into points, with little compromise of "recall" (typically zero), and a fast linear test, to help to discard quickly many of the false alarms that FastMap will typically introduce.

Efficient retrieval of similar shapes

TLDR
The experimental results showed the superiority of the indexing technique compared to search based on sequential scanning, which is the only obvious competitor, and the performance gain of the method increases with any increase in the number or the size of shapes.

Shape Similarity Measure Based on Correspondence of Visual Parts

TLDR
This work applied a cognitively motivated similarity measure to shape matching of object contours in various image databases and compared it to well-known approaches in the literature, justifying that the shape matching procedure gives an intuitive shape correspondence and is stable with respect to noise distortions.

Robust and Efficient Shape Indexing through Curvature Scale Space

TLDR
The matching algorithm which compares two sets of maxima and assigns a matching value as a measure of similarity is presented in this paper and introduces the aspect ratio of the CSS image as a new parameter which can be used for indexing in conjunction with other parameters like eccentricity and circularity.

Exact indexing of dynamic time warping

TLDR
This work introduces a novel technique for the exact indexing of Dynamic time warping and proves its vast superiority over all competing approaches in the largest and most comprehensive set of time series indexing experiments ever undertaken.

Retrieval by Shape Similarity with Perceptual Distance and Effective Indexing

TLDR
This paper proposes retrieval by shape similarity using local descriptors and effective indexing, and presents a comparative analysis of different indexing structures, for shape retrieval.

Distance sets for shape filters and shape recognition

TLDR
This work addresses two problems that are often encountered in object recognition: object segmentation, for which a distance sets shape filter is formulated, and shape matching, which is illustrated on printed and handwritten character recognition and detection of traffic signs in complex scenes.

Modified Fourier Descriptors for Shape Representation - A Practical Approach

TLDR
Experimental results suggest that the proposed Fourier Descriptor and metric is a feasible solution for on line shape comparisons in a content based image retrieval system.