Skip to Main Content
Tattoos provide an important source of biometric information, particularly in gang-related criminal activity. The goal of this paper is the formation of an image analysis tool to match tattoos and to retrieve similar tattoos from a tattoo database. First, an existing content based image retrieval (CBIR) approach for tattoos is reviewed. Then, a new active contour CBIR approach is detailed. This method incorporates vector field convolution active contours for tattoo segmentation, Haar wavelet decomposition for texture analysis, hue-saturation-value histograms for color representation and Fourier shape descriptors for shape characterization. Finally, the glocal (global-local) image feature approach is introduced. Results are provided for two datasets that include both recreational and prison/gang tattoos.