Computerized Matching of Shoeprints Based on Sole Pattern

Authors:
Rui Xiao;Pengfei Shi
Affiliations:
Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University, Shanghai, China 200240;Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University, Shanghai, China 200240
Venue:
IWCF '08 Proceedings of the 2nd international workshop on Computational Forensics
Year:
2008

Citing 3
Cited 0

On Image Analysis by the Methods of Moments

IEEE Transactions on Pattern Analysis and Machine Intelligence
Invariant Image Recognition by Zernike Moments

IEEE Transactions on Pattern Analysis and Machine Intelligence
Automated Processing of Shoeprint Images Based on the Fourier Transform for Use in Forensic Science

IEEE Transactions on Pattern Analysis and Machine Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

Shoeprints are common clues left at crime scenes that provide valuable evidence in detecting criminals. Traditional shoeprints matching algorithm is based on manual coding with limited recognition ability, and the results are strongly dependent on the operator. In this paper, a shoeprint matching method based on PSD (power spectral density) and Zernike moment have been investigated. The PSD method aims at pressing images and the legible shoeprints. The correlation coefficients of the PSD value of each image are used as the measurements of similarity. In addition, the Zernike method has been developed for blurred crime scene shoeprint images and shoeprints with complex backgrounds. A series of irregular shapes are employed to identify the shoeprints. Features are then selected according to the Zernike moments of these shapes. More than 400 real shoeprint images have been tested, experimental results support that the method is effective in shoeprint matching.