Shape retrieval using statistical chord-length features

Authors:
Chaojian Shi;Bin Wang
Affiliations:
Merchant Marine College, Shanghai Maritime University, Shanghai, P.R. China;Department of Computer Science and Engineering, Fudan University, Shanghai, P.R. China
Venue:
PSIVT'06 Proceedings of the First Pacific Rim conference on Advances in Image and Video Technology
Year:
2006

Citing 7
Cited 0

Pattern recognition with moment invariants: a comparative study and new results

Pattern Recognition
Shape measures for content based image retrieval: a comparison

Information Processing and Management: an International Journal
Visual information retrieval

Visual information retrieval
Techniques and Systems for Image and Video Retrieval

IEEE Transactions on Knowledge and Data Engineering
A Survey on Content-Based Retrieval for Multimedia Databases

IEEE Transactions on Knowledge and Data Engineering
Perceptual metrics for image database navigation

Perceptual metrics for image database navigation
Aircraft identification by moment invariants

IEEE Transactions on Computers

Quantified Score

Hi-index	0.00

Visualization

Abstract

A novel shape description method, statistical chord-length features (SCLF), is proposed for shape retrieval. SCLF first describes the contour of a 2D shape using k/2 one-dimensional chord-length functions derived from partitioning the contour into k arcs of the same length, where k is the parameter of SCLF. The means and variances of all the chord-length functions are then calculated and a k dimensional feature vector is generated as a shape descriptor. Two experiments are conducted and the results show that SCLF achieves higher retrieval performance than traditional description methods such as geometric moment invariants and Fourier descriptors.